## 2015 |

Martino, Luca; Elvira, Victor; Luengo, David; Artés-Rodríguez, Antonio; Corander, Jukka Smelly Parallel MCMC Chains Inproceedings 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4070–4074, IEEE, Brisbane, 2015, ISBN: 978-1-4673-6997-8. Abstract | Links | BibTeX | Tags: Bayesian inference, learning (artificial intelligence), Machine learning, Markov chain Monte Carlo, Markov chain Monte Carlo algorithms, Markov processes, MC methods, MCMC algorithms, MCMC scheme, mean square error, mean square error methods, Monte Carlo methods, optimisation, parallel and interacting chains, Probability density function, Proposals, robustness, Sampling methods, Signal processing, Signal processing algorithms, signal sampling, smelly parallel chains, smelly parallel MCMC chains, Stochastic optimization @inproceedings{Martino2015a, title = {Smelly Parallel MCMC Chains}, author = {Luca Martino and Victor Elvira and David Luengo and Antonio Artés-Rodríguez and Jukka Corander}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7178736 http://www.tsc.uc3m.es/~velvira/papers/ICASSP2015_martino.pdf}, doi = {10.1109/ICASSP.2015.7178736}, isbn = {978-1-4673-6997-8}, year = {2015}, date = {2015-04-01}, booktitle = {2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages = {4070--4074}, publisher = {IEEE}, address = {Brisbane}, abstract = {Monte Carlo (MC) methods are useful tools for Bayesian inference and stochastic optimization that have been widely applied in signal processing and machine learning. A well-known class of MC methods are Markov Chain Monte Carlo (MCMC) algorithms. In this work, we introduce a novel parallel interacting MCMC scheme, where the parallel chains share information, thus yielding a faster exploration of the state space. The interaction is carried out generating a dynamic repulsion among the “smelly” parallel chains that takes into account the entire population of current states. The ergodicity of the scheme and its relationship with other sampling methods are discussed. Numerical results show the advantages of the proposed approach in terms of mean square error, robustness w.r.t. to initial values and parameter choice.}, keywords = {Bayesian inference, learning (artificial intelligence), Machine learning, Markov chain Monte Carlo, Markov chain Monte Carlo algorithms, Markov processes, MC methods, MCMC algorithms, MCMC scheme, mean square error, mean square error methods, Monte Carlo methods, optimisation, parallel and interacting chains, Probability density function, Proposals, robustness, Sampling methods, Signal processing, Signal processing algorithms, signal sampling, smelly parallel chains, smelly parallel MCMC chains, Stochastic optimization}, pubstate = {published}, tppubtype = {inproceedings} } Monte Carlo (MC) methods are useful tools for Bayesian inference and stochastic optimization that have been widely applied in signal processing and machine learning. A well-known class of MC methods are Markov Chain Monte Carlo (MCMC) algorithms. In this work, we introduce a novel parallel interacting MCMC scheme, where the parallel chains share information, thus yielding a faster exploration of the state space. The interaction is carried out generating a dynamic repulsion among the “smelly” parallel chains that takes into account the entire population of current states. The ergodicity of the scheme and its relationship with other sampling methods are discussed. Numerical results show the advantages of the proposed approach in terms of mean square error, robustness w.r.t. to initial values and parameter choice. |

## 2010 |

Djuric, Petar M; Closas, Pau; Bugallo, Monica F; Miguez, Joaquin Evaluation of a Method's Robustness Inproceedings 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3598–3601, IEEE, Dallas, 2010, ISSN: 1520-6149. Abstract | Links | BibTeX | Tags: Electronic mail, Extraterrestrial measurements, Filtering, Gaussian processes, method's robustness, Random variables, robustness, sequential methods, Signal processing, statistical distributions, Telecommunications, uniform distribution, Wireless communication @inproceedings{Djuric2010, title = {Evaluation of a Method's Robustness}, author = {Petar M Djuric and Pau Closas and Monica F Bugallo and Joaquin Miguez}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5495921}, issn = {1520-6149}, year = {2010}, date = {2010-01-01}, booktitle = {2010 IEEE International Conference on Acoustics, Speech and Signal Processing}, pages = {3598--3601}, publisher = {IEEE}, address = {Dallas}, abstract = {In signal processing, it is typical to develop or use a method based on a given model. In practice, however, we almost never know the actual model and we hope that the assumed model is in the neighborhood of the true one. If deviations exist, the method may be more or less sensitive to them. Therefore, it is important to know more about this sensitivity, or in other words, how robust the method is to model deviations. To that end, it is useful to have a metric that can quantify the robustness of the method. In this paper we propose a procedure for developing a variety of metrics for measuring robustness. They are based on a discrete random variable that is generated from observed data and data generated according to past data and the adopted model. This random variable is uniform if the model is correct. When the model deviates from the true one, the distribution of the random variable deviates from the uniform distribution. One can then employ measures for differences between distributions in order to quantify robustness. In this paper we describe the proposed methodology and demonstrate it with simulated data.}, keywords = {Electronic mail, Extraterrestrial measurements, Filtering, Gaussian processes, method's robustness, Random variables, robustness, sequential methods, Signal processing, statistical distributions, Telecommunications, uniform distribution, Wireless communication}, pubstate = {published}, tppubtype = {inproceedings} } In signal processing, it is typical to develop or use a method based on a given model. In practice, however, we almost never know the actual model and we hope that the assumed model is in the neighborhood of the true one. If deviations exist, the method may be more or less sensitive to them. Therefore, it is important to know more about this sensitivity, or in other words, how robust the method is to model deviations. To that end, it is useful to have a metric that can quantify the robustness of the method. In this paper we propose a procedure for developing a variety of metrics for measuring robustness. They are based on a discrete random variable that is generated from observed data and data generated according to past data and the adopted model. This random variable is uniform if the model is correct. When the model deviates from the true one, the distribution of the random variable deviates from the uniform distribution. One can then employ measures for differences between distributions in order to quantify robustness. In this paper we describe the proposed methodology and demonstrate it with simulated data. |

## 2009 |

Djuric, Petar M; Bugallo, Monica F; Closas, Pau; Miguez, Joaquin Measuring the Robustness of Sequential Methods Inproceedings 2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, pp. 29–32, IEEE, Aruba, Dutch Antilles, 2009, ISBN: 978-1-4244-5179-1. Abstract | Links | BibTeX | Tags: Additive noise, cumulative distribution functions, data processing method, extended Kalman filtering, Extraterrestrial measurements, Filtering, Gaussian distribution, Gaussian noise, Kalman filters, Kolmogorov-Smirnov distance, Least squares approximation, Noise robustness, nonlinear filters, robustness, sequential methods, statistical distributions, telecommunication computing @inproceedings{Djuric2009a, title = {Measuring the Robustness of Sequential Methods}, author = {Petar M Djuric and Monica F Bugallo and Pau Closas and Joaquin Miguez}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5413275}, isbn = {978-1-4244-5179-1}, year = {2009}, date = {2009-01-01}, booktitle = {2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop}, pages = {29--32}, publisher = {IEEE}, address = {Aruba, Dutch Antilles}, abstract = {Whenever we apply methods for processing data, we make a number of model assumptions. In reality, these assumptions are not always correct. Robust methods can withstand model inaccuracies, that is, despite some incorrect assumptions they can still produce good results. We often want to know how robust employed methods are. To that end we need to have a yardstick for measuring robustness. In this paper, we propose an approach for constructing such metrics for sequential methods. These metrics are derived from the Kolmogorov-Smirnov distance between the cumulative distribution functions of the actual observations and the ones based on the assumed model. The use of the proposed metrics is demonstrated with simulation examples.}, keywords = {Additive noise, cumulative distribution functions, data processing method, extended Kalman filtering, Extraterrestrial measurements, Filtering, Gaussian distribution, Gaussian noise, Kalman filters, Kolmogorov-Smirnov distance, Least squares approximation, Noise robustness, nonlinear filters, robustness, sequential methods, statistical distributions, telecommunication computing}, pubstate = {published}, tppubtype = {inproceedings} } Whenever we apply methods for processing data, we make a number of model assumptions. In reality, these assumptions are not always correct. Robust methods can withstand model inaccuracies, that is, despite some incorrect assumptions they can still produce good results. We often want to know how robust employed methods are. To that end we need to have a yardstick for measuring robustness. In this paper, we propose an approach for constructing such metrics for sequential methods. These metrics are derived from the Kolmogorov-Smirnov distance between the cumulative distribution functions of the actual observations and the ones based on the assumed model. The use of the proposed metrics is demonstrated with simulation examples. |

Perez-Cruz, Fernando; Kulkarni, S R Distributed Least Square for Consensus Building in Sensor Networks Inproceedings 2009 IEEE International Symposium on Information Theory, pp. 2877–2881, IEEE, Seoul, 2009, ISBN: 978-1-4244-4312-3. Abstract | Links | BibTeX | Tags: Change detection algorithms, Channel Coding, Distributed computing, distributed least square method, graphical models, Inference algorithms, Kernel, Least squares methods, nonparametric statistics, Parametric statistics, robustness, sensor-network learning, statistical analysis, Telecommunication network reliability, Wireless sensor network, Wireless Sensor Networks @inproceedings{Perez-Cruz2009, title = {Distributed Least Square for Consensus Building in Sensor Networks}, author = {Fernando Perez-Cruz and S R Kulkarni}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5205336}, isbn = {978-1-4244-4312-3}, year = {2009}, date = {2009-01-01}, booktitle = {2009 IEEE International Symposium on Information Theory}, pages = {2877--2881}, publisher = {IEEE}, address = {Seoul}, abstract = {We present a novel mechanism for consensus building in sensor networks. The proposed algorithm has three main properties that make it suitable for general sensor-network learning. First, the proposed algorithm is based on robust nonparametric statistics and thereby needs little prior knowledge about the network and the function that needs to be estimated. Second, the algorithm uses only local information about the network and it communicates only with nearby sensors. Third, the algorithm is completely asynchronous and robust. It does not need to coordinate the sensors to estimate the underlying function and it is not affected if other sensors in the network stop working. Therefore, the proposed algorithm is an ideal candidate for sensor networks deployed in remote and inaccessible areas, which might need to change their objective once they have been set up.}, keywords = {Change detection algorithms, Channel Coding, Distributed computing, distributed least square method, graphical models, Inference algorithms, Kernel, Least squares methods, nonparametric statistics, Parametric statistics, robustness, sensor-network learning, statistical analysis, Telecommunication network reliability, Wireless sensor network, Wireless Sensor Networks}, pubstate = {published}, tppubtype = {inproceedings} } We present a novel mechanism for consensus building in sensor networks. The proposed algorithm has three main properties that make it suitable for general sensor-network learning. First, the proposed algorithm is based on robust nonparametric statistics and thereby needs little prior knowledge about the network and the function that needs to be estimated. Second, the algorithm uses only local information about the network and it communicates only with nearby sensors. Third, the algorithm is completely asynchronous and robust. It does not need to coordinate the sensors to estimate the underlying function and it is not affected if other sensors in the network stop working. Therefore, the proposed algorithm is an ideal candidate for sensor networks deployed in remote and inaccessible areas, which might need to change their objective once they have been set up. |