2025
Vary, Simon; Martínez-Rubio, David; Rebeschini, Patrick
Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization Proceedings Article
En: Li, Yingzhen; Mandt, Stephan; Agrawal, Shipra; Khan, Emtiyaz (Ed.): Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, pp. 4942–4950, PMLR, 2025.
Resumen | Enlaces | BibTeX | Etiquetas:
@inproceedings{pmlr-v258-vary25ab,
title = {Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization},
author = {Simon Vary and David Mart\'{i}nez-Rubio and Patrick Rebeschini},
editor = {Yingzhen Li and Stephan Mandt and Shipra Agrawal and Emtiyaz Khan},
url = {https://proceedings.mlr.press/v258/vary25a.html},
year = {2025},
date = {2025-05-01},
booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics},
volume = {258},
pages = {4942\textendash4950},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
abstract = {We study first-order algorithms that are uniformly stable for empirical risk minimization (ERM) problems that are convex and smooth with respect to $p$-norms, $p geq 1$. We propose a black-box reduction method that, by employing properties of uniformly convex regularizers, turns an optimization algorithm for H\"{o}lder smooth convex losses into a uniformly stable learning algorithm with optimal statistical risk bounds on the excess risk, up to a constant factor depending on $p$. Achieving a black-box reduction for uniform stability was posed as an open question by Attia and Koren (2022), which had solved the Euclidean case $p=2$. We explore applications that leverage non-Euclidean geometry in addressing binary classification problems.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We study first-order algorithms that are uniformly stable for empirical risk minimization (ERM) problems that are convex and smooth with respect to $p$-norms, $p geq 1$. We propose a black-box reduction method that, by employing properties of uniformly convex regularizers, turns an optimization algorithm for Hölder smooth convex losses into a uniformly stable learning algorithm with optimal statistical risk bounds on the excess risk, up to a constant factor depending on $p$. Achieving a black-box reduction for uniform stability was posed as an open question by Attia and Koren (2022), which had solved the Euclidean case $p=2$. We explore applications that leverage non-Euclidean geometry in addressing binary classification problems.
Vary, Simon; Martínez-Rubio, David; Rebeschini, Patrick
Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization Proceedings Article
En: Li, Yingzhen; Mandt, Stephan; Agrawal, Shipra; Khan, Emtiyaz (Ed.): Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, pp. 4942–4950, PMLR, 2025.
Resumen | Enlaces | BibTeX | Etiquetas:
@inproceedings{pmlr-v258-vary25a,
title = {Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization},
author = {Simon Vary and David Mart\'{i}nez-Rubio and Patrick Rebeschini},
editor = {Yingzhen Li and Stephan Mandt and Shipra Agrawal and Emtiyaz Khan},
url = {https://proceedings.mlr.press/v258/vary25a.html},
year = {2025},
date = {2025-05-01},
booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics},
volume = {258},
pages = {4942\textendash4950},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
abstract = {We study first-order algorithms that are uniformly stable for empirical risk minimization (ERM) problems that are convex and smooth with respect to $p$-norms, $p geq 1$. We propose a black-box reduction method that, by employing properties of uniformly convex regularizers, turns an optimization algorithm for H\"{o}lder smooth convex losses into a uniformly stable learning algorithm with optimal statistical risk bounds on the excess risk, up to a constant factor depending on $p$. Achieving a black-box reduction for uniform stability was posed as an open question by Attia and Koren (2022), which had solved the Euclidean case $p=2$. We explore applications that leverage non-Euclidean geometry in addressing binary classification problems.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We study first-order algorithms that are uniformly stable for empirical risk minimization (ERM) problems that are convex and smooth with respect to $p$-norms, $p geq 1$. We propose a black-box reduction method that, by employing properties of uniformly convex regularizers, turns an optimization algorithm for Hölder smooth convex losses into a uniformly stable learning algorithm with optimal statistical risk bounds on the excess risk, up to a constant factor depending on $p$. Achieving a black-box reduction for uniform stability was posed as an open question by Attia and Koren (2022), which had solved the Euclidean case $p=2$. We explore applications that leverage non-Euclidean geometry in addressing binary classification problems.
Martínez-Rubio, David; Roux, Christophe; Criscitiello, Christopher; Pokutta, Sebastian
Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties Proceedings Article
En: Li, Yingzhen; Mandt, Stephan; Agrawal, Shipra; Khan, Emtiyaz (Ed.): Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, pp. 280–288, PMLR, 2025.
Resumen | Enlaces | BibTeX | Etiquetas:
@inproceedings{pmlr-v258-martinez-rubio25a,
title = {Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties},
author = {David Mart\'{i}nez-Rubio and Christophe Roux and Christopher Criscitiello and Sebastian Pokutta},
editor = {Yingzhen Li and Stephan Mandt and Shipra Agrawal and Emtiyaz Khan},
url = {https://proceedings.mlr.press/v258/martinez-rubio25a.html},
year = {2025},
date = {2025-05-01},
urldate = {2025-05-01},
booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics},
volume = {258},
pages = {280\textendash288},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
abstract = {In this work, we study optimization problems of the form $min_x max_y f(x, y)$, where $f(x, y)$ is defined on a product Riemannian manifold $mathcalM times mathcalN$ and is $mu_x$-strongly geodesically convex (g-convex) in $x$ and $mu_y$-strongly g-concave in $y$, for $mu_x, mu_y geq 0$. We design accelerated methods when $f$ is $(L_x, L_y, L_xy)$-smooth and $mathcalM$, $mathcalN$ are Hadamard. To that aim we introduce new g-convex optimization results, of independent interest: we show global linear convergence for metric-projected Riemannian gradient descent and improve existing accelerated methods by reducing geometric constants. Additionally, we complete the analysis of two previous works applying to the Riemannian min-max case by removing an assumption about iterates staying in a pre-specified compact set.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this work, we study optimization problems of the form $min_x max_y f(x, y)$, where $f(x, y)$ is defined on a product Riemannian manifold $mathcalM times mathcalN$ and is $mu_x$-strongly geodesically convex (g-convex) in $x$ and $mu_y$-strongly g-concave in $y$, for $mu_x, mu_y geq 0$. We design accelerated methods when $f$ is $(L_x, L_y, L_xy)$-smooth and $mathcalM$, $mathcalN$ are Hadamard. To that aim we introduce new g-convex optimization results, of independent interest: we show global linear convergence for metric-projected Riemannian gradient descent and improve existing accelerated methods by reducing geometric constants. Additionally, we complete the analysis of two previous works applying to the Riemannian min-max case by removing an assumption about iterates staying in a pre-specified compact set.
Paz-Arbaizar, Leire; Lopez-Castroman, Jorge; Artés-Rodríguez, Antonio; Olmos, Pablo M; Ramírez, David
Emotion Forecasting: A Transformer-Based Approach Artículo de revista
En: J Med Internet Res, vol. 27, pp. e63962, 2025, ISSN: 1438-8871.
Resumen | Enlaces | BibTeX | Etiquetas: affect; emotional valence; machine learning; mental disorder; monitoring; mood; passive data; Patient Health Questionnaire-9; PHQ-9; psychological distress; time-series forecasting
@article{info:doi/10.2196/63962,
title = {Emotion Forecasting: A Transformer-Based Approach},
author = {Leire Paz-Arbaizar and Jorge Lopez-Castroman and Antonio Art\'{e}s-Rodr\'{i}guez and Pablo M Olmos and David Ram\'{i}rez},
url = {https://doi.org/10.2196/63962},
doi = {10.2196/63962},
issn = {1438-8871},
year = {2025},
date = {2025-03-18},
journal = {J Med Internet Res},
volume = {27},
pages = {e63962},
abstract = {Background: Monitoring the emotional states of patients with psychiatric problems has always been challenging due to the noncontinuous nature of clinical assessments, the effect of the health care environment, and the inherent subjectivity of evaluation instruments. However, mental states in psychiatric disorders exhibit substantial variability over time, making real-time monitoring crucial for preventing risky situations and ensuring appropriate treatment. Objective: This study aimed to leverage new technologies and deep learning techniques to enable more objective, real-time monitoring of patients. This was achieved by passively monitoring variables such as step count, patient location, and sleep patterns using mobile devices. We aimed to predict patient self-reports and detect sudden variations in their emotional valence, identifying situations that may require clinical intervention. Methods: Data for this project were collected using the Evidence-Based Behavior (eB2) app, which records both passive and self-reported variables daily. Passive data refer to behavioral information gathered via the eB2 app through sensors embedded in mobile devices and wearables. These data were obtained from studies conducted in collaboration with hospitals and clinics that used eB2. We used hidden Markov models (HMMs) to address missing data and transformer deep neural networks for time-series forecasting. Finally, classification algorithms were applied to predict several variables, including emotional state and responses to the Patient Health Questionnaire-9. Results: Through real-time patient monitoring, we demonstrated the ability to accurately predict patients' emotional states and anticipate changes over time. Specifically, our approach achieved high accuracy (0.93) and a receiver operating characteristic (ROC) area under the curve (AUC) of 0.98 for emotional valence classification. For predicting emotional state changes 1 day in advance, we obtained an ROC AUC of 0.87. Furthermore, we demonstrated the feasibility of forecasting responses to the Patient Health Questionnaire-9, with particularly strong performance for certain questions. For example, in question 9, related to suicidal ideation, our model achieved an accuracy of 0.9 and an ROC AUC of 0.77 for predicting the next day's response. Moreover, we illustrated the enhanced stability of multivariate time-series forecasting when HMM preprocessing was combined with a transformer model, as opposed to other time-series forecasting methods, such as recurrent neural networks or long short-term memory cells. Conclusions: The stability of multivariate time-series forecasting improved when HMM preprocessing was combined with a transformer model, as opposed to other time-series forecasting methods (eg, recurrent neural network and long short-term memory), leveraging the attention mechanisms to capture longer time dependencies and gain interpretability. We showed the potential to assess the emotional state of a patient and the scores of psychiatric questionnaires from passive variables in advance. This allows real-time monitoring of patients and hence better risk detection and treatment adjustment.},
keywords = {affect; emotional valence; machine learning; mental disorder; monitoring; mood; passive data; Patient Health Questionnaire-9; PHQ-9; psychological distress; time-series forecasting},
pubstate = {published},
tppubtype = {article}
}
Background: Monitoring the emotional states of patients with psychiatric problems has always been challenging due to the noncontinuous nature of clinical assessments, the effect of the health care environment, and the inherent subjectivity of evaluation instruments. However, mental states in psychiatric disorders exhibit substantial variability over time, making real-time monitoring crucial for preventing risky situations and ensuring appropriate treatment. Objective: This study aimed to leverage new technologies and deep learning techniques to enable more objective, real-time monitoring of patients. This was achieved by passively monitoring variables such as step count, patient location, and sleep patterns using mobile devices. We aimed to predict patient self-reports and detect sudden variations in their emotional valence, identifying situations that may require clinical intervention. Methods: Data for this project were collected using the Evidence-Based Behavior (eB2) app, which records both passive and self-reported variables daily. Passive data refer to behavioral information gathered via the eB2 app through sensors embedded in mobile devices and wearables. These data were obtained from studies conducted in collaboration with hospitals and clinics that used eB2. We used hidden Markov models (HMMs) to address missing data and transformer deep neural networks for time-series forecasting. Finally, classification algorithms were applied to predict several variables, including emotional state and responses to the Patient Health Questionnaire-9. Results: Through real-time patient monitoring, we demonstrated the ability to accurately predict patients' emotional states and anticipate changes over time. Specifically, our approach achieved high accuracy (0.93) and a receiver operating characteristic (ROC) area under the curve (AUC) of 0.98 for emotional valence classification. For predicting emotional state changes 1 day in advance, we obtained an ROC AUC of 0.87. Furthermore, we demonstrated the feasibility of forecasting responses to the Patient Health Questionnaire-9, with particularly strong performance for certain questions. For example, in question 9, related to suicidal ideation, our model achieved an accuracy of 0.9 and an ROC AUC of 0.77 for predicting the next day's response. Moreover, we illustrated the enhanced stability of multivariate time-series forecasting when HMM preprocessing was combined with a transformer model, as opposed to other time-series forecasting methods, such as recurrent neural networks or long short-term memory cells. Conclusions: The stability of multivariate time-series forecasting improved when HMM preprocessing was combined with a transformer model, as opposed to other time-series forecasting methods (eg, recurrent neural network and long short-term memory), leveraging the attention mechanisms to capture longer time dependencies and gain interpretability. We showed the potential to assess the emotional state of a patient and the scores of psychiatric questionnaires from passive variables in advance. This allows real-time monitoring of patients and hence better risk detection and treatment adjustment.
Gonzalez, Fabian; Akyildiz, O. Deniz; Crisan, Dan; Miguez, Joaquin
Nudging state-space models for Bayesian filtering under misspecified dynamics Miscelánea
2025.
@misc{gonzalez2025nudgingstatespacemodelsbayesian,
title = {Nudging state-space models for Bayesian filtering under misspecified dynamics},
author = {Fabian Gonzalez and O. Deniz Akyildiz and Dan Crisan and Joaquin Miguez},
url = {https://arxiv.org/abs/2411.00218},
year = {2025},
date = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Gallego-Viñarás, Lorena; Mira-Tomás, Juan Miguel; Gaeta, Anna Michela; Pinol-Ripoll, Gerard; Barbé, Ferran; Olmos, Pablo M.; Muñoz-Barrutia, Arrate
Alzheimer's Disease Detection in EEG Sleep Signals Artículo de revista
En: IEEE Journal of Biomedical and Health Informatics, vol. 29, no 2, pp. 948-959, 2025.
Enlaces | BibTeX | Etiquetas: Sleep;Electroencephalography;Brain modeling;Databases;Data models;Predictive models;Band-pass filters;Alzheimer's disease;Electrodes;Recording;Alzheimer's disease (AD);Deep Learning (DL);Electroencephalogram (EEG);Mild Cognitive Impairment (MCI);polysomnography (PSG);semi-supervised models
@article{10714019b,
title = {Alzheimer's Disease Detection in EEG Sleep Signals},
author = {Lorena Gallego-Vi\~{n}ar\'{a}s and Juan Miguel Mira-Tom\'{a}s and Anna Michela Gaeta and Gerard Pinol-Ripoll and Ferran Barb\'{e} and Pablo M. Olmos and Arrate Mu\~{n}oz-Barrutia},
doi = {10.1109/JBHI.2024.3478380},
year = {2025},
date = {2025-01-01},
journal = {IEEE Journal of Biomedical and Health Informatics},
volume = {29},
number = {2},
pages = {948-959},
keywords = {Sleep;Electroencephalography;Brain modeling;Databases;Data models;Predictive models;Band-pass filters;Alzheimer\'s disease;Electrodes;Recording;Alzheimer\'s disease (AD);Deep Learning (DL);Electroencephalogram (EEG);Mild Cognitive Impairment (MCI);polysomnography (PSG);semi-supervised models},
pubstate = {published},
tppubtype = {article}
}
Gallego-Viñarás, Lorena; Mira-Tomás, Juan Miguel; Gaeta, Anna Michela; Pinol-Ripoll, Gerard; Barbé, Ferran; Olmos, Pablo M.; Muñoz-Barrutia, Arrate
Alzheimer's Disease Detection in EEG Sleep Signals Artículo de revista
En: IEEE Journal of Biomedical and Health Informatics, vol. 29, no 2, pp. 948-959, 2025.
Enlaces | BibTeX | Etiquetas: Sleep;Electroencephalography;Brain modeling;Databases;Data models;Predictive models;Band-pass filters;Alzheimer's disease;Electrodes;Recording;Alzheimer's disease (AD);Deep Learning (DL);Electroencephalogram (EEG);Mild Cognitive Impairment (MCI);polysomnography (PSG);semi-supervised models
@article{10714019,
title = {Alzheimer's Disease Detection in EEG Sleep Signals},
author = {Lorena Gallego-Vi\~{n}ar\'{a}s and Juan Miguel Mira-Tom\'{a}s and Anna Michela Gaeta and Gerard Pinol-Ripoll and Ferran Barb\'{e} and Pablo M. Olmos and Arrate Mu\~{n}oz-Barrutia},
doi = {10.1109/JBHI.2024.3478380},
year = {2025},
date = {2025-01-01},
journal = {IEEE Journal of Biomedical and Health Informatics},
volume = {29},
number = {2},
pages = {948-959},
keywords = {Sleep;Electroencephalography;Brain modeling;Databases;Data models;Predictive models;Band-pass filters;Alzheimer\'s disease;Electrodes;Recording;Alzheimer\'s disease (AD);Deep Learning (DL);Electroencephalogram (EEG);Mild Cognitive Impairment (MCI);polysomnography (PSG);semi-supervised models},
pubstate = {published},
tppubtype = {article}
}
Oliver, Rodrigo; Pérez-Sabater, Josué; Paz-Arbaizar, Leire; Lancho, Alejandro; Artés, Antonio; Olmos, Pablo M.
A Foundation Model for Patient Behavior Monitoring and Suicide Detection Miscelánea
2025.
@misc{oliver2025foundationmodelpatientbehavior,
title = {A Foundation Model for Patient Behavior Monitoring and Suicide Detection},
author = {Rodrigo Oliver and Josu\'{e} P\'{e}rez-Sabater and Leire Paz-Arbaizar and Alejandro Lancho and Antonio Art\'{e}s and Pablo M. Olmos},
url = {https://arxiv.org/abs/2503.15221},
year = {2025},
date = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Larese, Darío C.; Cerrada, Almudena Bravo; Tomei, Gabriel Dambrosio; Guerrero-López, Alejandro; Olmos, Pablo M.; García, María Jesús Gómez
Transformer Vibration Forecasting for Advancing Rail Safety and Maintenance 4.0 Miscelánea
2025.
@misc{larese2025transformervibrationforecastingadvancing,
title = {Transformer Vibration Forecasting for Advancing Rail Safety and Maintenance 4.0},
author = {Dar\'{i}o C. Larese and Almudena Bravo Cerrada and Gabriel Dambrosio Tomei and Alejandro Guerrero-L\'{o}pez and Pablo M. Olmos and Mar\'{i}a Jes\'{u}s G\'{o}mez Garc\'{i}a},
url = {https://arxiv.org/abs/2501.11730},
year = {2025},
date = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Yang, Zi; Li, Ying; Lin, Zhidi; Zhang, Michael Minyi; Olmos, Pablo M.
Multi-View Oriented GPLVM: Expressiveness and Efficiency Miscelánea
2025.
@misc{yang2025multivieworientedgplvmexpressiveness,
title = {Multi-View Oriented GPLVM: Expressiveness and Efficiency},
author = {Zi Yang and Ying Li and Zhidi Lin and Michael Minyi Zhang and Pablo M. Olmos},
url = {https://arxiv.org/abs/2502.08253},
year = {2025},
date = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Lancho, Alejandro; Weiss, Amir; Lee, Gary C. F.; Jayashankar, Tejas; Kurien, Binoy G.; Polyanskiy, Yury; Wornell, Gregory W.
RF Challenge: The Data-Driven Radio Frequency Signal Separation Challenge Artículo de revista
En: IEEE Open Journal of the Communications Society, vol. 6, pp. 4083–4100, 2025, ISSN: 2644-125X.
@article{Lancho_2025,
title = {RF Challenge: The Data-Driven Radio Frequency Signal Separation Challenge},
author = {Alejandro Lancho and Amir Weiss and Gary C. F. Lee and Tejas Jayashankar and Binoy G. Kurien and Yury Polyanskiy and Gregory W. Wornell},
url = {http://dx.doi.org/10.1109/OJCOMS.2025.3556319},
doi = {10.1109/ojcoms.2025.3556319},
issn = {2644-125X},
year = {2025},
date = {2025-01-01},
journal = {IEEE Open Journal of the Communications Society},
volume = {6},
pages = {4083\textendash4100},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Paz-Arbaizar, L.; López-Castromán, Jorge; Artés-Rodríguez, A.; Olmos, Pablo M; Ramírez, D.
Emotion forecasting: A transformer-based approach Artículo de revista
En: J. Med. Internet Res., vol. 27, pp. e63962, 2025.
@article{Paz-ArbaizarLopez-CastromanArtes-Rodriguez-2025-Emotionforecastingtransformer-basedapproach,
title = {Emotion forecasting: A transformer-based approach},
author = {L. Paz-Arbaizar and Jorge L\'{o}pez-Castrom\'{a}n and A. Art\'{e}s-Rodr\'{i}guez and Pablo M Olmos and D. Ram\'{i}rez},
doi = {10.2196/63962},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {J. Med. Internet Res.},
volume = {27},
pages = {e63962},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2024
Frutos, José Manuel; Olmos, Pablo; Lopez, Manuel Alberto Vazquez; Míguez, Joaquín
Training Implicit Generative Models via an Invariant Statistical Loss Proceedings Article
En: Dasgupta, Sanjoy; Mandt, Stephan; Li, Yingzhen (Ed.): Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, pp. 2026–2034, PMLR, 2024.
Resumen | Enlaces | BibTeX | Etiquetas:
@inproceedings{pmlr-v238-frutos24a,
title = {Training Implicit Generative Models via an Invariant Statistical Loss},
author = {Jos\'{e} Manuel Frutos and Pablo Olmos and Manuel Alberto Vazquez Lopez and Joaqu\'{i}n M\'{i}guez},
editor = {Sanjoy Dasgupta and Stephan Mandt and Yingzhen Li},
url = {https://proceedings.mlr.press/v238/frutos24a.html},
year = {2024},
date = {2024-05-01},
booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics},
volume = {238},
pages = {2026\textendash2034},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
abstract = {Implicit generative models have the capability to learn arbitrary complex data distributions. On the downside, training requires telling apart real data from artificially-generated ones using adversarial discriminators, leading to unstable training and mode-dropping issues. As reported by Zahee et al. (2017), even in the one-dimensional (1D) case, training a generative adversarial network (GAN) is challenging and often suboptimal. In this work, we develop a discriminator-free method for training one-dimensional (1D) generative implicit models and subsequently expand this method to accommodate multivariate cases. Our loss function is a discrepancy measure between a suitably chosen transformation of the model samples and a uniform distribution; hence, it is invariant with respect to the true distribution of the data. We first formulate our method for 1D random variables, providing an effective solution for approximate reparameterization of arbitrary complex distributions. Then, we consider the temporal setting (both univariate and multivariate), in which we model the conditional distribution of each sample given the history of the process. We demonstrate through numerical simulations that this new method yields promising results, successfully learning true distributions in a variety of scenarios and mitigating some of the well-known problems that state-of-the-art implicit methods present.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Implicit generative models have the capability to learn arbitrary complex data distributions. On the downside, training requires telling apart real data from artificially-generated ones using adversarial discriminators, leading to unstable training and mode-dropping issues. As reported by Zahee et al. (2017), even in the one-dimensional (1D) case, training a generative adversarial network (GAN) is challenging and often suboptimal. In this work, we develop a discriminator-free method for training one-dimensional (1D) generative implicit models and subsequently expand this method to accommodate multivariate cases. Our loss function is a discrepancy measure between a suitably chosen transformation of the model samples and a uniform distribution; hence, it is invariant with respect to the true distribution of the data. We first formulate our method for 1D random variables, providing an effective solution for approximate reparameterization of arbitrary complex distributions. Then, we consider the temporal setting (both univariate and multivariate), in which we model the conditional distribution of each sample given the history of the process. We demonstrate through numerical simulations that this new method yields promising results, successfully learning true distributions in a variety of scenarios and mitigating some of the well-known problems that state-of-the-art implicit methods present.
Ramírez, David; Santamaria, Ignacio; Scharf, Louis L
Passive Detection of a Random Signal Common to Multi-Sensor Reference and Surveillance Arrays Artículo de revista
En: IEEE transactions on vehicular technology., vol. 73, no 7, pp. 10106–10117, 2024, ISSN: 0018-9545.
BibTeX | Etiquetas:
@article{Ram\'{i}rezDavid2024PDoa,
title = {Passive Detection of a Random Signal Common to Multi-Sensor Reference and Surveillance Arrays},
author = {David Ram\'{i}rez and Ignacio Santamaria and Louis L Scharf},
issn = {0018-9545},
year = {2024},
date = {2024-01-01},
journal = {IEEE transactions on vehicular technology.},
volume = {73},
number = {7},
pages = {10106\textendash10117},
publisher = {Institute of Electrical and Electronics Engineers},
address = {New York :},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Miguez, Joaquín; Molina-Bulla, Harold; Mariño, Inés P
Master-slave coupling scheme for synchronization and parameter estimation in the generalized Kuramoto-Sivashinsky equation Artículo de revista
En: Physical review special topics. PRST-AB., vol. 110, no 5, pp. 054206, 2024, ISSN: 2470-0045.
BibTeX | Etiquetas:
@article{MiguezJoaqu\'{i}n2024Mcsf,
title = {Master-slave coupling scheme for synchronization and parameter estimation in the generalized Kuramoto-Sivashinsky equation},
author = {Joaqu\'{i}n Miguez and Harold Molina-Bulla and In\'{e}s P Mari\~{n}o},
issn = {2470-0045},
year = {2024},
date = {2024-01-01},
journal = {Physical review special topics. PRST-AB.},
volume = {110},
number = {5},
pages = {054206},
publisher = {American Physical Society,},
address = {Ridge, N.Y. :},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Lopez-Castroman, Jorge; Artés-Rodríguez, Antonio; Courtet, Philippe; Hanon, Cecile; Gondek, Tomasz; Baca-García, Enrique; Volpe, Umberto
The growing need to integrate digital mental health into psychiatric and medical education Artículo de revista
En: European Psychiatry, vol. 67, no 1, pp. e90, 2024.
@article{Lopez-Castroman_Art\'{e}s-Rodr\'{i}guez_Courtet_Hanon_Gondek_Baca-Garc\'{i}a_Volpe_2024,
title = {The growing need to integrate digital mental health into psychiatric and medical education},
author = {Jorge Lopez-Castroman and Antonio Art\'{e}s-Rodr\'{i}guez and Philippe Courtet and Cecile Hanon and Tomasz Gondek and Enrique Baca-Garc\'{i}a and Umberto Volpe},
doi = {10.1192/j.eurpsy.2024.1802},
year = {2024},
date = {2024-01-01},
journal = {European Psychiatry},
volume = {67},
number = {1},
pages = {e90},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Muñiz, Paula; Martínez-García, María; Bailén, Rebeca; Chicano, María; Oarbeascoa, Gillen; Triviño, Juan Carlos; Sebastian, Ismael Iglesia-San; de Córdoba, Sara Fernández; Anguita, Javier; Kwon, Mi; Díez-Martín, José Luis; Olmos, Pablo M.; Martínez-Laperche, Carolina; Buño, Ismael
En: Frontiers in Immunology, vol. Volume 15 - 2024, 2024, ISSN: 1664-3224.
Resumen | Enlaces | BibTeX | Etiquetas:
@article{10.3389/fimmu.2024.1396284,
title = {Identification of predictive models including polymorphisms in cytokines genes and clinical variables associated with post-transplant complications after identical HLA-allogeneic stem cell transplantation},
author = {Paula Mu\~{n}iz and Mar\'{i}a Mart\'{i}nez-Garc\'{i}a and Rebeca Bail\'{e}n and Mar\'{i}a Chicano and Gillen Oarbeascoa and Juan Carlos Trivi\~{n}o and Ismael Iglesia-San Sebastian and Sara Fern\'{a}ndez de C\'{o}rdoba and Javier Anguita and Mi Kwon and Jos\'{e} Luis D\'{i}ez-Mart\'{i}n and Pablo M. Olmos and Carolina Mart\'{i}nez-Laperche and Ismael Bu\~{n}o},
url = {https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2024.1396284},
doi = {10.3389/fimmu.2024.1396284},
issn = {1664-3224},
year = {2024},
date = {2024-01-01},
journal = {Frontiers in Immunology},
volume = {Volume 15 - 2024},
abstract = {\<sec\>\<title\>Backgrounds\</title\>\<p\>Although allogeneic hematopoietic stem cell transplantation (allo-HSCT) is a potentially curative therapy for hematological malignancies, it can be associated with relevant post-transplant complications. Several reports have shown that polymorphisms in immune system genes are correlated with the development of post-transplant complications. Within this context, this work focuses on identifying novel polymorphisms in cytokine genes and developing predictive models to anticipate the risk of developing graft-versus-host disease (GVHD), transplantation-related mortality (TRM), relapse and overall survival (OS).\</p\>\</sec\>\<sec\>\<title\>Methods\</title\>\<p\>Our group developed a 132-cytokine gene panel which was tested in 90 patients who underwent an HLA-identical sibling-donor allo-HSCT. Bayesian logistic regression (BLR) models were used to select the most relevant variables. Based on the cut-off points selected for each model, patients were classified as being at high or low-risk for each of the post-transplant complications (aGVHD II-IV, aGVHD III-IV, cGVHD, mod-sev cGVHD, TRM, relapse and OS).\</p\>\</sec\>\<sec\>\<title\>Results\</title\>\<p\>A total of 737 polymorphisms were selected from the custom panel genes. Of these, 41 polymorphisms were included in the predictive models in 30 cytokine genes were selected (17 interleukins and 13 chemokines). Of these polymorphisms, 5 (12.2%) were located in coding regions, and 36 (87.8%) in non-coding regions. All models had a statistical significance of p\<0.0001.\</p\>\</sec\>\<sec\>\<title\>Conclusion\</title\>\<p\>Overall, genomic polymorphisms in cytokine genes make it possible to anticipate the development all complications studied following allo-HSCT and, consequently, to optimize the clinical management of patients.\</p\>\</sec\>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<sec><title>Backgrounds</title><p>Although allogeneic hematopoietic stem cell transplantation (allo-HSCT) is a potentially curative therapy for hematological malignancies, it can be associated with relevant post-transplant complications. Several reports have shown that polymorphisms in immune system genes are correlated with the development of post-transplant complications. Within this context, this work focuses on identifying novel polymorphisms in cytokine genes and developing predictive models to anticipate the risk of developing graft-versus-host disease (GVHD), transplantation-related mortality (TRM), relapse and overall survival (OS).</p></sec><sec><title>Methods</title><p>Our group developed a 132-cytokine gene panel which was tested in 90 patients who underwent an HLA-identical sibling-donor allo-HSCT. Bayesian logistic regression (BLR) models were used to select the most relevant variables. Based on the cut-off points selected for each model, patients were classified as being at high or low-risk for each of the post-transplant complications (aGVHD II-IV, aGVHD III-IV, cGVHD, mod-sev cGVHD, TRM, relapse and OS).</p></sec><sec><title>Results</title><p>A total of 737 polymorphisms were selected from the custom panel genes. Of these, 41 polymorphisms were included in the predictive models in 30 cytokine genes were selected (17 interleukins and 13 chemokines). Of these polymorphisms, 5 (12.2%) were located in coding regions, and 36 (87.8%) in non-coding regions. All models had a statistical significance of p<0.0001.</p></sec><sec><title>Conclusion</title><p>Overall, genomic polymorphisms in cytokine genes make it possible to anticipate the development all complications studied following allo-HSCT and, consequently, to optimize the clinical management of patients.</p></sec>
Rocamora, Elias Abad; Liu, Fanghui; Chrysos, Grigorios G.; Olmos, Pablo M.; Cevher, Volkan
Efficient local linearity regularization to overcome catastrophic overfitting Miscelánea
2024.
@misc{rocamora2024efficientlocallinearityregularization,
title = {Efficient local linearity regularization to overcome catastrophic overfitting},
author = {Elias Abad Rocamora and Fanghui Liu and Grigorios G. Chrysos and Pablo M. Olmos and Volkan Cevher},
url = {https://arxiv.org/abs/2401.11618},
year = {2024},
date = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Frutos, José Manuel; Olmos, Pablo M.; Vázquez, Manuel A.; Míguez, Joaquín
Training Implicit Generative Models via an Invariant Statistical Loss Miscelánea
2024.
@misc{defrutos2024trainingimplicitgenerativemodelsb,
title = {Training Implicit Generative Models via an Invariant Statistical Loss},
author = {Jos\'{e} Manuel Frutos and Pablo M. Olmos and Manuel A. V\'{a}zquez and Joaqu\'{i}n M\'{i}guez},
url = {https://arxiv.org/abs/2402.16435},
year = {2024},
date = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Frutos, José Manuel; Olmos, Pablo M.; Vázquez, Manuel A.; Míguez, Joaquín
Training Implicit Generative Models via an Invariant Statistical Loss Miscelánea
2024.
@misc{defrutos2024trainingimplicitgenerativemodels,
title = {Training Implicit Generative Models via an Invariant Statistical Loss},
author = {Jos\'{e} Manuel Frutos and Pablo M. Olmos and Manuel A. V\'{a}zquez and Joaqu\'{i}n M\'{i}guez},
url = {https://arxiv.org/abs/2402.16435},
year = {2024},
date = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Jordahn, Mikkel; Olmos, Pablo M.
Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks Miscelánea
2024.
@misc{jordahn2024decouplingfeatureextractionclassification,
title = {Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks},
author = {Mikkel Jordahn and Pablo M. Olmos},
url = {https://arxiv.org/abs/2405.01196},
year = {2024},
date = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Gallego-Viñarás, Lorena; Michela-Gaeta, Anna; Pinol-Ripoll, Gerard; Barbé, Ferrán; Olmos, Pablo M.; Muñoz-Barrutia, Arrate
Calibration Methods for Alzheimer Disease Detection Proceedings Article
En: 2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1-6, 2024.
Enlaces | BibTeX | Etiquetas: Measurement;Histograms;Accuracy;Sleep;Predictive models;Brain modeling;Electroencephalography;Calibration;Reliability;Alzheimer's disease;Alzheimer's disease (AD);Deep Neural Networks (DNN);Electro Encephalogram (EEG);Polysomnography (PSG);calibration;confidences
@inproceedings{10734829,
title = {Calibration Methods for Alzheimer Disease Detection},
author = {Lorena Gallego-Vi\~{n}ar\'{a}s and Anna Michela-Gaeta and Gerard Pinol-Ripoll and Ferr\'{a}n Barb\'{e} and Pablo M. Olmos and Arrate Mu\~{n}oz-Barrutia},
doi = {10.1109/MLSP58920.2024.10734829},
year = {2024},
date = {2024-01-01},
booktitle = {2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)},
pages = {1-6},
keywords = {Measurement;Histograms;Accuracy;Sleep;Predictive models;Brain modeling;Electroencephalography;Calibration;Reliability;Alzheimer\'s disease;Alzheimer\'s disease (AD);Deep Neural Networks (DNN);Electro Encephalogram (EEG);Polysomnography (PSG);calibration;confidences},
pubstate = {published},
tppubtype = {inproceedings}
}
Martínez-García, María; Villacrés, Grace; Mitchell, David; Olmos, Pablo M.
Protect Before Generate: Error Correcting Codes within Discrete Deep Generative Models Miscelánea
2024.
@misc{mart\'{i}nezgarc\'{i}a2024protectgenerateerrorcorrecting,
title = {Protect Before Generate: Error Correcting Codes within Discrete Deep Generative Models},
author = {Mar\'{i}a Mart\'{i}nez-Garc\'{i}a and Grace Villacr\'{e}s and David Mitchell and Pablo M. Olmos},
url = {https://arxiv.org/abs/2410.07840},
year = {2024},
date = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Li, Ying; Lin, Zhidi; Liu, Yuhao; Zhang, Michael Minyi; Olmos, Pablo M.; Djurić, Petar M.
Scalable Random Feature Latent Variable Models Miscelánea
2024.
@misc{li2024scalablerandomfeaturelatent,
title = {Scalable Random Feature Latent Variable Models},
author = {Ying Li and Zhidi Lin and Yuhao Liu and Michael Minyi Zhang and Pablo M. Olmos and Petar M. Djuri\'{c}},
url = {https://arxiv.org/abs/2410.17700},
year = {2024},
date = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Frutos, José Manuel; Vázquez, Manuel A.; Olmos, Pablo; Míguez, Joaquín
2024.
@misc{defrutos2024robusttrainingimplicitgenerative,
title = {Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical loss},
author = {Jos\'{e} Manuel Frutos and Manuel A. V\'{a}zquez and Pablo Olmos and Joaqu\'{i}n M\'{i}guez},
url = {https://arxiv.org/abs/2410.22381},
year = {2024},
date = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Sanderson, Daniel; Olmos, Pablo; Cerro, Carlos Fernández Del; Desco, Manuel; Abella, Monica
Diffusion X-ray image denoising Proceedings Article
En: 2024.
BibTeX | Etiquetas:
@inproceedings{inproceedings,
title = {Diffusion X-ray image denoising},
author = {Daniel Sanderson and Pablo Olmos and Carlos Fern\'{a}ndez Del Cerro and Manuel Desco and Monica Abella},
year = {2024},
date = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Jayashankar, Tejas; Lee, Gary C. F.; Lancho, Alejandro; Weiss, Amir; Polyanskiy, Yury; Wornell, Gregory W.
Score-based Source Separation with Applications to Digital Communication Signals Miscelánea
2024.
@misc{jayashankar2024scorebasedsourceseparationapplications,
title = {Score-based Source Separation with Applications to Digital Communication Signals},
author = {Tejas Jayashankar and Gary C. F. Lee and Alejandro Lancho and Amir Weiss and Yury Polyanskiy and Gregory W. Wornell},
url = {https://arxiv.org/abs/2306.14411},
year = {2024},
date = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Jayashankar, Tejas; Kurien, Binoy; Lancho, Alejandro; Lee, Gary C. F.; Polyanskiy, Yury; Weiss, Amir; Wornell, Gregory W.
The Data-Driven Radio Frequency Signal Separation Challenge Proceedings Article
En: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), pp. 53-54, 2024.
Enlaces | BibTeX | Etiquetas: Radio frequency;Knowledge engineering;Source separation;Interference cancellation;RF signals;Neural networks;Modulation;Source separation;interference rejection;machine learning;wireless communication
@inproceedings{10627554,
title = {The Data-Driven Radio Frequency Signal Separation Challenge},
author = {Tejas Jayashankar and Binoy Kurien and Alejandro Lancho and Gary C. F. Lee and Yury Polyanskiy and Amir Weiss and Gregory W. Wornell},
doi = {10.1109/ICASSPW62465.2024.10627554},
year = {2024},
date = {2024-01-01},
booktitle = {2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)},
pages = {53-54},
keywords = {Radio frequency;Knowledge engineering;Source separation;Interference cancellation;RF signals;Neural networks;Modulation;Source separation;interference rejection;machine learning;wireless communication},
pubstate = {published},
tppubtype = {inproceedings}
}
Stanton, G.; Ramírez, D.; Santamaría, I.; Scharf, L. L.; Wang, H.
Multi-channel factor analysis: Identifiability and asymptotics Artículo de revista
En: IEEE Trans. Signal Process., vol. 72, pp. 3562–3577, 2024, ISSN: 1053-587X.
@article{StantonRamirezSantamaria-2024-Multi-channelfactoranalysisIdentifiabilityand,
title = {Multi-channel factor analysis: Identifiability and asymptotics},
author = {G. Stanton and D. Ram\'{i}rez and I. Santamar\'{i}a and L. L. Scharf and H. Wang},
doi = {10.1109/TSP.2024.3427004},
issn = {1053-587X},
year = {2024},
date = {2024-01-01},
journal = {IEEE Trans. Signal Process.},
volume = {72},
pages = {3562\textendash3577},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Xiao, Y. -H.; Ramírez, D.; Huang, L.; Li, X. -P.; So, H. C.
One-bit target detection in colocated MIMO radar with colored background noise Artículo de revista
En: IEEE Trans. Signal Process., vol. 72, pp. 5274–5290, 2024, ISSN: 1053-587X.
@article{XiaoRamirezHuang-2024-One-bittargetdetectionincolocated,
title = {One-bit target detection in colocated MIMO radar with colored background noise},
author = {Y. -H. Xiao and D. Ram\'{i}rez and L. Huang and X. -P. Li and H. C. So},
doi = {10.1109/TSP.2024.3484582},
issn = {1053-587X},
year = {2024},
date = {2024-01-01},
journal = {IEEE Trans. Signal Process.},
volume = {72},
pages = {5274\textendash5290},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Wu, P. -W.; Huang, L.; Ramírez, David; Xiao, Y. -H.; So, H. C.
One-bit spectrum sensing for cognitive radio Artículo de revista
En: IEEE Trans. Signal Process., vol. 72, pp. 549–564, 2024, ISSN: 1053-587X.
@article{WuHuangRamirez-2024-One-bitspectrumsensingforcognitive,
title = {One-bit spectrum sensing for cognitive radio},
author = {P. -W. Wu and L. Huang and David Ram\'{i}rez and Y. -H. Xiao and H. C. So},
doi = {10.1109/TSP.2023.3343569},
issn = {1053-587X},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
journal = {IEEE Trans. Signal Process.},
volume = {72},
pages = {549\textendash564},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Garcia, Yannick Sztamfater; Rivo, Manuel Sanjurjo; Miguez, Joaquin; Escribano, Guillermo
Novel method for the Computation of In-Orbit Collision Probability by Multilevel Splitting and Surrogate Modelling Proceedings Article
En: AIAA SCITECH 2024 Forum, pp. 1813, 2024.
BibTeX | Etiquetas:
@inproceedings{sztamfater2024novel,
title = {Novel method for the Computation of In-Orbit Collision Probability by Multilevel Splitting and Surrogate Modelling},
author = {Yannick Sztamfater Garcia and Manuel Sanjurjo Rivo and Joaquin Miguez and Guillermo Escribano},
year = {2024},
date = {2024-01-01},
booktitle = {AIAA SCITECH 2024 Forum},
pages = {1813},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Porras-Segovia, Alejandro; Granda-Beltrán, Ana Maria De; Gallardo, Claudia; Abascal-Peiró, Sofía; Barrigón, María Luisa; Artés-Rodríguez, Antonio; López-Castroman, Jorge; Courtet, Philippe; Baca-García, Enrique
Smartphone-based safety plan for suicidal crisis: The SmartCrisis 2.0 pilot study Artículo de revista
En: Journal of Psychiatric Research, vol. 169, pp. 284-291, 2024, ISSN: 0022-3956.
Resumen | Enlaces | BibTeX | Etiquetas: Ecological momentary intervention, Experience-sampling method, Suicide, Suicide attempt, Suicide ideation, Time-sampling procedures
@article{PORRASSEGOVIA2024284,
title = {Smartphone-based safety plan for suicidal crisis: The SmartCrisis 2.0 pilot study},
author = {Alejandro Porras-Segovia and Ana Maria De Granda-Beltr\'{a}n and Claudia Gallardo and Sof\'{i}a Abascal-Peir\'{o} and Mar\'{i}a Luisa Barrig\'{o}n and Antonio Art\'{e}s-Rodr\'{i}guez and Jorge L\'{o}pez-Castroman and Philippe Courtet and Enrique Baca-Garc\'{i}a},
url = {https://www.sciencedirect.com/science/article/pii/S0022395623005526},
doi = {https://doi.org/10.1016/j.jpsychires.2023.11.039},
issn = {0022-3956},
year = {2024},
date = {2024-01-01},
journal = {Journal of Psychiatric Research},
volume = {169},
pages = {284-291},
abstract = {Here we present the findings of the pilot phase of the SmartCrisis 2.0 Randomized Clinical Trial. This pilot study aimed to explore the feasibility and acceptability of a safety plan contained in a smartphone app. Our sample consisted patients with a history of recent suicidal behaviour who installed a smartphone-based safety plan. To explore the satisfaction with of the safety plan, two patient satisfaction surveys were conducted: one qualitative and one quantitative. To explore the objective use of the safety plan, we gained access to texts contained in the safety plans completed by the patients. Participation rate was 77%, while 48.9% patients completed both satisfaction surveys at the end of the pilot phase. N = 105 successfully installed the safety plan. In a scale from 1 to 10, users rated the usefulness of the security plan at 7.4, the usability at 8.9, the degree to which they would recommend it to others at 8.6 and the overall satisfaction with the project including evaluations at 9.6. The most widely completed tab was warning signs. Feeling sad or lonely was the warning sign most commonly reported by patients. The second most completed tab was internal coping strategies. Walking or practicing any other exercise was the strategy most commonly resorted to. Our smartphone-based safety plan appears to be a feasible intervention. Data obtained from this pilot study showed high participation rates and high acceptability by patients. This, together with the general satisfaction with the project, supports its implementation in the clinical practice.},
keywords = {Ecological momentary intervention, Experience-sampling method, Suicide, Suicide attempt, Suicide ideation, Time-sampling procedures},
pubstate = {published},
tppubtype = {article}
}
Here we present the findings of the pilot phase of the SmartCrisis 2.0 Randomized Clinical Trial. This pilot study aimed to explore the feasibility and acceptability of a safety plan contained in a smartphone app. Our sample consisted patients with a history of recent suicidal behaviour who installed a smartphone-based safety plan. To explore the satisfaction with of the safety plan, two patient satisfaction surveys were conducted: one qualitative and one quantitative. To explore the objective use of the safety plan, we gained access to texts contained in the safety plans completed by the patients. Participation rate was 77%, while 48.9% patients completed both satisfaction surveys at the end of the pilot phase. N = 105 successfully installed the safety plan. In a scale from 1 to 10, users rated the usefulness of the security plan at 7.4, the usability at 8.9, the degree to which they would recommend it to others at 8.6 and the overall satisfaction with the project including evaluations at 9.6. The most widely completed tab was warning signs. Feeling sad or lonely was the warning sign most commonly reported by patients. The second most completed tab was internal coping strategies. Walking or practicing any other exercise was the strategy most commonly resorted to. Our smartphone-based safety plan appears to be a feasible intervention. Data obtained from this pilot study showed high participation rates and high acceptability by patients. This, together with the general satisfaction with the project, supports its implementation in the clinical practice.
2023
Lancho, Alejandro; Durisi, Giuseppe; Sanguinetti, Luca
Cell-Free Massive MIMO for URLLC: A Finite-Blocklength Analysis Artículo de revista
En: IEEE Transactions on Wireless Communications, vol. 22, no 12, pp. 8723–8735, 2023, ISSN: 1558-2248.
@article{Lancho_2023,
title = {Cell-Free Massive MIMO for URLLC: A Finite-Blocklength Analysis},
author = {Alejandro Lancho and Giuseppe Durisi and Luca Sanguinetti},
url = {http://dx.doi.org/10.1109/TWC.2023.3265303},
doi = {10.1109/twc.2023.3265303},
issn = {1558-2248},
year = {2023},
date = {2023-12-01},
journal = {IEEE Transactions on Wireless Communications},
volume = {22},
number = {12},
pages = {8723\textendash8735},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Xiao, Y. -H.; Huang, L.; Ramírez, David; Qian, C.; So, H. C.
Covariance matrix recovery from one-bit data with non-zero quantization thresholds: Algorithm and performance analysis Artículo de revista
En: IEEE Trans. Signal Process., vol. 71, pp. 4060–4076, 2023, ISSN: 1053-587X.
@article{XiaoHuangRamirez-2023-Covariancematrixrecoveryfromone-bit,
title = {Covariance matrix recovery from one-bit data with non-zero quantization thresholds: Algorithm and performance analysis},
author = {Y. -H. Xiao and L. Huang and David Ram\'{i}rez and C. Qian and H. C. So},
doi = {10.1109/TSP.2023.3325664},
issn = {1053-587X},
year = {2023},
date = {2023-11-01},
journal = {IEEE Trans. Signal Process.},
volume = {71},
pages = {4060\textendash4076},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Sükei, Emese; Romero-Medrano, Lorena; Leon-Martinez, Santiago; López, Jesús Herrera; Campaña-Montes, Juan José; Olmos, Pablo M; Baca-Garcia, Enrique; Artés, Antonio
Continuous Assessment of Function and Disability via Mobile Sensing: Real-World Data-Driven Feasibility Study Artículo de revista
En: JMIR Form Res, vol. 7, pp. e47167, 2023, ISSN: 2561-326X.
Resumen | Enlaces | BibTeX | Etiquetas: WHODAS; functional limitations; mobile sensing; passive ecological momentary assessment; predictive modeling; interpretable machine learning; machine learning; disability; clinical outcome
@article{info:doi/10.2196/47167b,
title = {Continuous Assessment of Function and Disability via Mobile Sensing: Real-World Data-Driven Feasibility Study},
author = {Emese S\"{u}kei and Lorena Romero-Medrano and Santiago Leon-Martinez and Jes\'{u}s Herrera L\'{o}pez and Juan Jos\'{e} Campa\~{n}a-Montes and Pablo M Olmos and Enrique Baca-Garcia and Antonio Art\'{e}s},
url = {http://www.ncbi.nlm.nih.gov/pubmed/37902823},
doi = {10.2196/47167},
issn = {2561-326X},
year = {2023},
date = {2023-10-30},
journal = {JMIR Form Res},
volume = {7},
pages = {e47167},
abstract = {Background: Functional limitations are associated with poor clinical outcomes, higher mortality, and disability rates, especially in older adults. Continuous assessment of patients' functionality is important for clinical practice; however, traditional questionnaire-based assessment methods are very time-consuming and infrequently used. Mobile sensing offers a great range of sources that can assess function and disability daily. Objective: This work aims to prove the feasibility of an interpretable machine learning pipeline for predicting function and disability based on the World Health Organization Disability Assessment Schedule (WHODAS) 2.0 outcomes of clinical outpatients, using passively collected digital biomarkers. Methods: One-month-long behavioral time-series data consisting of physical and digital activity descriptor variables were summarized using statistical measures (minimum, maximum, mean, median, SD, and IQR), creating 64 features that were used for prediction. We then applied a sequential feature selection to each WHODAS 2.0 domain (cognition, mobility, self-care, getting along, life activities, and participation) in order to find the most descriptive features for each domain. Finally, we predicted the WHODAS 2.0 functional domain scores using linear regression using the best feature subsets. We reported the mean absolute errors and the mean absolute percentage errors over 4 folds as goodness-of-fit statistics to evaluate the model and allow for between-domain performance comparison. Results: Our machine learning\textendashbased models for predicting patients' WHODAS functionality scores per domain achieved an average (across the 6 domains) mean absolute percentage error of 19.5%, varying between 14.86% (self-care domain) and 27.21% (life activities domain). We found that 5-19 features were sufficient for each domain, and the most relevant being the distance traveled, time spent at home, time spent walking, exercise time, and vehicle time. Conclusions: Our findings show the feasibility of using machine learning\textendashbased methods to assess functional health solely from passively sensed mobile data. The feature selection step provides a set of interpretable features for each domain, ensuring better explainability to the models' decisions\textemdashan important aspect in clinical practice.},
keywords = {WHODAS; functional limitations; mobile sensing; passive ecological momentary assessment; predictive modeling; interpretable machine learning; machine learning; disability; clinical outcome},
pubstate = {published},
tppubtype = {article}
}
Background: Functional limitations are associated with poor clinical outcomes, higher mortality, and disability rates, especially in older adults. Continuous assessment of patients' functionality is important for clinical practice; however, traditional questionnaire-based assessment methods are very time-consuming and infrequently used. Mobile sensing offers a great range of sources that can assess function and disability daily. Objective: This work aims to prove the feasibility of an interpretable machine learning pipeline for predicting function and disability based on the World Health Organization Disability Assessment Schedule (WHODAS) 2.0 outcomes of clinical outpatients, using passively collected digital biomarkers. Methods: One-month-long behavioral time-series data consisting of physical and digital activity descriptor variables were summarized using statistical measures (minimum, maximum, mean, median, SD, and IQR), creating 64 features that were used for prediction. We then applied a sequential feature selection to each WHODAS 2.0 domain (cognition, mobility, self-care, getting along, life activities, and participation) in order to find the most descriptive features for each domain. Finally, we predicted the WHODAS 2.0 functional domain scores using linear regression using the best feature subsets. We reported the mean absolute errors and the mean absolute percentage errors over 4 folds as goodness-of-fit statistics to evaluate the model and allow for between-domain performance comparison. Results: Our machine learning–based models for predicting patients' WHODAS functionality scores per domain achieved an average (across the 6 domains) mean absolute percentage error of 19.5%, varying between 14.86% (self-care domain) and 27.21% (life activities domain). We found that 5-19 features were sufficient for each domain, and the most relevant being the distance traveled, time spent at home, time spent walking, exercise time, and vehicle time. Conclusions: Our findings show the feasibility of using machine learning–based methods to assess functional health solely from passively sensed mobile data. The feature selection step provides a set of interpretable features for each domain, ensuring better explainability to the models' decisions—an important aspect in clinical practice.
Sükei, Emese; Romero-Medrano, Lorena; Leon-Martinez, Santiago; López, Jesús Herrera; Campaña-Montes, Juan José; Olmos, Pablo M; Baca-Garcia, Enrique; Artés-Rodríguez, Antonio
Continuous Assessment of Function and Disability via Mobile Sensing: Real-World Data-Driven Feasibility Study Artículo de revista
En: JMIR Form Res, vol. 7, pp. e47167, 2023, ISSN: 2561-326X.
Resumen | Enlaces | BibTeX | Etiquetas: WHODAS; functional limitations; mobile sensing; passive ecological momentary assessment; predictive modeling; interpretable machine learning; machine learning; disability; clinical outcome
@article{info:doi/10.2196/47167,
title = {Continuous Assessment of Function and Disability via Mobile Sensing: Real-World Data-Driven Feasibility Study},
author = {Emese S\"{u}kei and Lorena Romero-Medrano and Santiago Leon-Martinez and Jes\'{u}s Herrera L\'{o}pez and Juan Jos\'{e} Campa\~{n}a-Montes and Pablo M Olmos and Enrique Baca-Garcia and Antonio Art\'{e}s-Rodr\'{i}guez},
url = {http://www.ncbi.nlm.nih.gov/pubmed/37902823},
doi = {10.2196/47167},
issn = {2561-326X},
year = {2023},
date = {2023-10-30},
journal = {JMIR Form Res},
volume = {7},
pages = {e47167},
abstract = {Background: Functional limitations are associated with poor clinical outcomes, higher mortality, and disability rates, especially in older adults. Continuous assessment of patients' functionality is important for clinical practice; however, traditional questionnaire-based assessment methods are very time-consuming and infrequently used. Mobile sensing offers a great range of sources that can assess function and disability daily. Objective: This work aims to prove the feasibility of an interpretable machine learning pipeline for predicting function and disability based on the World Health Organization Disability Assessment Schedule (WHODAS) 2.0 outcomes of clinical outpatients, using passively collected digital biomarkers. Methods: One-month-long behavioral time-series data consisting of physical and digital activity descriptor variables were summarized using statistical measures (minimum, maximum, mean, median, SD, and IQR), creating 64 features that were used for prediction. We then applied a sequential feature selection to each WHODAS 2.0 domain (cognition, mobility, self-care, getting along, life activities, and participation) in order to find the most descriptive features for each domain. Finally, we predicted the WHODAS 2.0 functional domain scores using linear regression using the best feature subsets. We reported the mean absolute errors and the mean absolute percentage errors over 4 folds as goodness-of-fit statistics to evaluate the model and allow for between-domain performance comparison. Results: Our machine learning\textendashbased models for predicting patients' WHODAS functionality scores per domain achieved an average (across the 6 domains) mean absolute percentage error of 19.5%, varying between 14.86% (self-care domain) and 27.21% (life activities domain). We found that 5-19 features were sufficient for each domain, and the most relevant being the distance traveled, time spent at home, time spent walking, exercise time, and vehicle time. Conclusions: Our findings show the feasibility of using machine learning\textendashbased methods to assess functional health solely from passively sensed mobile data. The feature selection step provides a set of interpretable features for each domain, ensuring better explainability to the models' decisions\textemdashan important aspect in clinical practice.},
keywords = {WHODAS; functional limitations; mobile sensing; passive ecological momentary assessment; predictive modeling; interpretable machine learning; machine learning; disability; clinical outcome},
pubstate = {published},
tppubtype = {article}
}
Background: Functional limitations are associated with poor clinical outcomes, higher mortality, and disability rates, especially in older adults. Continuous assessment of patients' functionality is important for clinical practice; however, traditional questionnaire-based assessment methods are very time-consuming and infrequently used. Mobile sensing offers a great range of sources that can assess function and disability daily. Objective: This work aims to prove the feasibility of an interpretable machine learning pipeline for predicting function and disability based on the World Health Organization Disability Assessment Schedule (WHODAS) 2.0 outcomes of clinical outpatients, using passively collected digital biomarkers. Methods: One-month-long behavioral time-series data consisting of physical and digital activity descriptor variables were summarized using statistical measures (minimum, maximum, mean, median, SD, and IQR), creating 64 features that were used for prediction. We then applied a sequential feature selection to each WHODAS 2.0 domain (cognition, mobility, self-care, getting along, life activities, and participation) in order to find the most descriptive features for each domain. Finally, we predicted the WHODAS 2.0 functional domain scores using linear regression using the best feature subsets. We reported the mean absolute errors and the mean absolute percentage errors over 4 folds as goodness-of-fit statistics to evaluate the model and allow for between-domain performance comparison. Results: Our machine learning–based models for predicting patients' WHODAS functionality scores per domain achieved an average (across the 6 domains) mean absolute percentage error of 19.5%, varying between 14.86% (self-care domain) and 27.21% (life activities domain). We found that 5-19 features were sufficient for each domain, and the most relevant being the distance traveled, time spent at home, time spent walking, exercise time, and vehicle time. Conclusions: Our findings show the feasibility of using machine learning–based methods to assess functional health solely from passively sensed mobile data. The feature selection step provides a set of interpretable features for each domain, ensuring better explainability to the models' decisions—an important aspect in clinical practice.
Kislal, A. Oguz; Lancho, Alejandro; Durisi, Giuseppe; Ström, Erik G.
Efficient Evaluation of the Error Probability for Pilot-Assisted URLLC With Massive MIMO Artículo de revista
En: IEEE Journal on Selected Areas in Communications, vol. 41, no 7, pp. 1969–1981, 2023, ISSN: 1558-0008.
@article{Kislal_2023,
title = {Efficient Evaluation of the Error Probability for Pilot-Assisted URLLC With Massive MIMO},
author = {A. Oguz Kislal and Alejandro Lancho and Giuseppe Durisi and Erik G. Str\"{o}m},
url = {http://dx.doi.org/10.1109/JSAC.2023.3280972},
doi = {10.1109/jsac.2023.3280972},
issn = {1558-0008},
year = {2023},
date = {2023-07-01},
journal = {IEEE Journal on Selected Areas in Communications},
volume = {41},
number = {7},
pages = {1969\textendash1981},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Barrigon, Maria Luisa; Romero-Medrano, Lorena; Moreno-Muñoz, Pablo; Porras-Segovia, Alejandro; Lopez-Castroman, Jorge; Courtet, Philippe; Artés-Rodríguez, Antonio; Baca-Garcia, Enrique
One-Week Suicide Risk Prediction Using Real-Time Smartphone Monitoring: Prospective Cohort Study Artículo de revista
En: J Med Internet Res, vol. 25, pp. e43719, 2023, ISSN: 1438-8871.
Resumen | Enlaces | BibTeX | Etiquetas: e-health; m-health; Ecological Mometary Asssessment; risk prediction; sensor monitoring; suicidal; suicide attempt; suicide
@article{info:doi/10.2196/43719,
title = {One-Week Suicide Risk Prediction Using Real-Time Smartphone Monitoring: Prospective Cohort Study},
author = {Maria Luisa Barrigon and Lorena Romero-Medrano and Pablo Moreno-Mu\~{n}oz and Alejandro Porras-Segovia and Jorge Lopez-Castroman and Philippe Courtet and Antonio Art\'{e}s-Rodr\'{i}guez and Enrique Baca-Garcia},
url = {http://www.ncbi.nlm.nih.gov/pubmed/37656498},
doi = {10.2196/43719},
issn = {1438-8871},
year = {2023},
date = {2023-05-01},
journal = {J Med Internet Res},
volume = {25},
pages = {e43719},
abstract = {Background: Suicide is a major global public health issue that is becoming increasingly common despite preventive efforts. Though current methods for predicting suicide risk are not sufficiently accurate, technological advances provide invaluable tools with which we may evolve toward a personalized, predictive approach. Objective: We aim to predict the short-term (1-week) risk of suicide by identifying changes in behavioral patterns characterized through real-time smartphone monitoring in a cohort of patients with suicidal ideation. Methods: We recruited 225 patients between February 2018 and March 2020 with a history of suicidal thoughts and behavior as part of the multicenter SmartCrisis study. Throughout 6 months of follow-up, we collected information on the risk of suicide or mental health crises. All participants underwent voluntary passive monitoring using data generated by their own smartphones, including distance walked and steps taken, time spent at home, and app usage. The algorithm constructs daily activity profiles for each patient according to these data and detects changes in the distribution of these profiles over time. Such changes are considered critical periods, and their relationship with suicide-risk events was tested. Results: During follow-up, 18 (8%) participants attempted suicide, and 14 (6.2%) presented to the emergency department for psychiatric care. The behavioral changes identified by the algorithm predicted suicide risk in a time frame of 1 week with an area under the curve of 0.78, indicating good accuracy. Conclusions: We describe an innovative method to identify mental health crises based on passively collected information from patients' smartphones. This technology could be applied to homogeneous groups of patients to identify different types of crises.},
keywords = {e-health; m-health; Ecological Mometary Asssessment; risk prediction; sensor monitoring; suicidal; suicide attempt; suicide},
pubstate = {published},
tppubtype = {article}
}
Background: Suicide is a major global public health issue that is becoming increasingly common despite preventive efforts. Though current methods for predicting suicide risk are not sufficiently accurate, technological advances provide invaluable tools with which we may evolve toward a personalized, predictive approach. Objective: We aim to predict the short-term (1-week) risk of suicide by identifying changes in behavioral patterns characterized through real-time smartphone monitoring in a cohort of patients with suicidal ideation. Methods: We recruited 225 patients between February 2018 and March 2020 with a history of suicidal thoughts and behavior as part of the multicenter SmartCrisis study. Throughout 6 months of follow-up, we collected information on the risk of suicide or mental health crises. All participants underwent voluntary passive monitoring using data generated by their own smartphones, including distance walked and steps taken, time spent at home, and app usage. The algorithm constructs daily activity profiles for each patient according to these data and detects changes in the distribution of these profiles over time. Such changes are considered critical periods, and their relationship with suicide-risk events was tested. Results: During follow-up, 18 (8%) participants attempted suicide, and 14 (6.2%) presented to the emergency department for psychiatric care. The behavioral changes identified by the algorithm predicted suicide risk in a time frame of 1 week with an area under the curve of 0.78, indicating good accuracy. Conclusions: We describe an innovative method to identify mental health crises based on passively collected information from patients' smartphones. This technology could be applied to homogeneous groups of patients to identify different types of crises.
Sánchez-Martín, Pablo; Olmos, Pablo M.; Perez-Cruz, Fernando
Enhancing diversity in GANs via non-uniform sampling Artículo de revista
En: Information Sciences, vol. 637, pp. 118928, 2023, ISSN: 0020-0255.
Resumen | Enlaces | BibTeX | Etiquetas: Deep generative models, Generative adversarial networks, Mode-collapse
@article{SANCHEZMARTIN2023118928b,
title = {Enhancing diversity in GANs via non-uniform sampling},
author = {Pablo S\'{a}nchez-Mart\'{i}n and Pablo M. Olmos and Fernando Perez-Cruz},
url = {https://www.sciencedirect.com/science/article/pii/S002002552300498X},
doi = {https://doi.org/10.1016/j.ins.2023.04.007},
issn = {0020-0255},
year = {2023},
date = {2023-01-01},
journal = {Information Sciences},
volume = {637},
pages = {118928},
abstract = {Recent advances in Generative Adversarial Networks (GANs) have led to impressive results in generating realistic data. However, GANs training is still challenging, often leading to mode-collapse, where a certain type of samples dominates the generated output. To address this issue, we propose a novel training algorithm based on bidirectional GANs (BiGANs) that can be generalized to any implicit generative model. Our algorithm relies on a non-uniform sampling scheme, where data points in a minibatch are sampled with probability inversely proportional to their log-evidence. However, estimating log-evidence is computationally expensive. Instead, we propose to use the reconstruction error, which directly correlates with the log-evidence and only requires a BiGAN network evaluation. Additionally, we combine the aforementioned method with a regularization in the empirical distribution of the encoder that further boosts the performance. Our empirical results show that the proposed methods improve both the quality and diversity of the generated samples.},
keywords = {Deep generative models, Generative adversarial networks, Mode-collapse},
pubstate = {published},
tppubtype = {article}
}
Recent advances in Generative Adversarial Networks (GANs) have led to impressive results in generating realistic data. However, GANs training is still challenging, often leading to mode-collapse, where a certain type of samples dominates the generated output. To address this issue, we propose a novel training algorithm based on bidirectional GANs (BiGANs) that can be generalized to any implicit generative model. Our algorithm relies on a non-uniform sampling scheme, where data points in a minibatch are sampled with probability inversely proportional to their log-evidence. However, estimating log-evidence is computationally expensive. Instead, we propose to use the reconstruction error, which directly correlates with the log-evidence and only requires a BiGAN network evaluation. Additionally, we combine the aforementioned method with a regularization in the empirical distribution of the encoder that further boosts the performance. Our empirical results show that the proposed methods improve both the quality and diversity of the generated samples.
Sükei, Emese; Leon-Martinez, Santiago; Olmos, Pablo; Rodríguez, Antonio Artés
Automatic patient functionality assessment from multimodal data using deep learning techniques – Development and feasibility evaluation Artículo de revista
En: Internet Interventions, vol. 33, pp. 100657, 2023.
@article{articlee,
title = {Automatic patient functionality assessment from multimodal data using deep learning techniques \textendash Development and feasibility evaluation},
author = {Emese S\"{u}kei and Santiago Leon-Martinez and Pablo Olmos and Antonio Art\'{e}s Rodr\'{i}guez},
doi = {10.1016/j.invent.2023.100657},
year = {2023},
date = {2023-01-01},
journal = {Internet Interventions},
volume = {33},
pages = {100657},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Rama, Óscar Jiménez; Moreno-Pino, Fernando; Ramírez, David; Olmos, Pablo M.
Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering Miscelánea
2023.
@misc{rama2023interpretablespectralvariationalautoencoder,
title = {Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering},
author = {\'{O}scar Jim\'{e}nez Rama and Fernando Moreno-Pino and David Ram\'{i}rez and Pablo M. Olmos},
url = {https://arxiv.org/abs/2310.11940},
year = {2023},
date = {2023-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Fengler, Alexander; Lancho, Alejandro; Polyanskiy, Yury
Coded Orthogonal Modulation for the Multi-Antenna Multiple-Access Channel Miscelánea
2023.
@misc{fengler2023codedorthogonalmodulationmultiantennab,
title = {Coded Orthogonal Modulation for the Multi-Antenna Multiple-Access Channel},
author = {Alexander Fengler and Alejandro Lancho and Yury Polyanskiy},
url = {https://arxiv.org/abs/2307.01095},
year = {2023},
date = {2023-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Lancho, Alejandro; Weiss, Amir; Lee, Gary CF
Mini RF Challenge Miscelánea
urlhttps://kaggle.com/competitions/mini-rf-challenge, 2023, (Kaggle).
BibTeX | Etiquetas:
@misc{mini-rf-challengeb,
title = {Mini RF Challenge},
author = {Alejandro Lancho and Amir Weiss and Gary CF Lee},
year = {2023},
date = {2023-01-01},
howpublished = {urlhttps://kaggle.com/competitions/mini-rf-challenge},
note = {Kaggle},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Fengler, Alexander; Lancho, Alejandro; Narayanan, Krishna; Polyanskiy, Yury
On the Advantages of Asynchrony in the Unsourced MAC Miscelánea
2023.
@misc{fengler2023advantagesasynchronyunsourcedmacb,
title = {On the Advantages of Asynchrony in the Unsourced MAC},
author = {Alexander Fengler and Alejandro Lancho and Krishna Narayanan and Yury Polyanskiy},
url = {https://arxiv.org/abs/2305.06985},
year = {2023},
date = {2023-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Weiss, Amir; Lancho, Alejandro; Bu, Yuheng; Wornell, Gregory W.
A Bilateral Bound on the Mean-Square Error for Estimation in Model Mismatch Miscelánea
2023.
@misc{weiss2023bilateralboundmeansquareerrorb,
title = {A Bilateral Bound on the Mean-Square Error for Estimation in Model Mismatch},
author = {Amir Weiss and Alejandro Lancho and Yuheng Bu and Gregory W. Wornell},
url = {https://arxiv.org/abs/2305.08207},
year = {2023},
date = {2023-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Weiss, Amir; Lancho, Alejandro; Bu, Yuheng; Wornell, Gregory W.
A Bilateral Bound on the Mean-Square Error for Estimation in Model Mismatch Miscelánea
2023.
@misc{weiss2023bilateralboundmeansquareerror,
title = {A Bilateral Bound on the Mean-Square Error for Estimation in Model Mismatch},
author = {Amir Weiss and Alejandro Lancho and Yuheng Bu and Gregory W. Wornell},
url = {https://arxiv.org/abs/2305.08207},
year = {2023},
date = {2023-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Lancho, Alejandro; Weiss, Amir; Lee, Gary CF
Mini RF Challenge Miscelánea
urlhttps://kaggle.com/competitions/mini-rf-challenge, 2023, (Kaggle).
BibTeX | Etiquetas:
@misc{mini-rf-challenge,
title = {Mini RF Challenge},
author = {Alejandro Lancho and Amir Weiss and Gary CF Lee},
year = {2023},
date = {2023-01-01},
howpublished = {urlhttps://kaggle.com/competitions/mini-rf-challenge},
note = {Kaggle},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Fengler, Alexander; Lancho, Alejandro; Narayanan, Krishna; Polyanskiy, Yury
On the Advantages of Asynchrony in the Unsourced MAC Miscelánea
2023.
@misc{fengler2023advantagesasynchronyunsourcedmac,
title = {On the Advantages of Asynchrony in the Unsourced MAC},
author = {Alexander Fengler and Alejandro Lancho and Krishna Narayanan and Yury Polyanskiy},
url = {https://arxiv.org/abs/2305.06985},
year = {2023},
date = {2023-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Ngo, Khac-Hoang; Lancho, Alejandro; Durisi, Giuseppe; Amat, Alexandre Graell
Unsourced Multiple Access With Random User Activity Miscelánea
2023.
@misc{ngo2023unsourcedmultipleaccessrandom,
title = {Unsourced Multiple Access With Random User Activity},
author = {Khac-Hoang Ngo and Alejandro Lancho and Giuseppe Durisi and Alexandre Graell Amat},
url = {https://arxiv.org/abs/2202.06365},
year = {2023},
date = {2023-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}