Timezone: »
Spectral estimation (SE) aims to identify how the energy of a signal (e.g., a time series) is distributed across different frequencies. This can become particularly challenging when only partial and noisy observations of the signal are available, where current methods fail to handle uncertainty appropriately. In this context, we propose a joint probabilistic model for signals, observations and spectra, where SE is addressed as an inference problem. Assuming a Gaussian process prior over the signal, we apply Bayes' rule to find the analytic posterior distribution of the spectrum given a set of observations. Besides its expressiveness and natural account of spectral uncertainty, the proposed model also provides a functional-form representation of the power spectral density, which can be optimised efficiently. Comparison with previous approaches is addressed theoretically, showing that the proposed method is an infinite-dimensional variant of the Lomb-Scargle approach, and also empirically through three experiments.
Author Information
Felipe Tobar (Universidad de Chile)
Felipe Tobar is an Assistant Professor at the Data & AI Initiative at Universidad de Chile. He holds Researcher positions at the Center for Mathematical Modeling and the Advanced Center for Electrical Engineering. Felipe received the BSc/MSc degrees in Electrical Engineering (U. de Chile, 2010) and a PhD in Signal Processing (Imperial College London, 2014), and he was an Associate Researcher in Machine Learning at the University of Cambridge (2014-2015). Felipe teaches Statistics and Machine Learning courses at undergraduate, graduate and professional levels. His research interests lie in the interface between Machine Learning and Statistical Signal Processing, including Gaussian processes, spectral estimation, approximate inference, Bayesian nonparametrics, and optimal transport.
Related Events (a corresponding poster, oral, or spotlight)
-
2018 Poster: Bayesian Nonparametric Spectral Estimation »
Tue. Dec 4th through Wed the 5th Room Room 517 AB #114
More from the Same Authors
-
2021 Poster: A novel notion of barycenter for probability distributions based on optimal weak mass transport »
Elsa Cazelles · Felipe Tobar · Joaquin Fontbona -
2021 : Concluding Remarks »
Felipe Tobar · César Lincoln Mattos -
2021 : Multioutput GPs »
Felipe Tobar -
2021 : Implementation of a GP »
Felipe Tobar -
2021 : Choosing the Kernel and Learning its Parameters »
Felipe Tobar -
2021 : Infinitely-many Gaussian RVs: The Gaussian process »
Felipe Tobar -
2021 : From One to Finitely-Many Gaussian RVs »
Felipe Tobar -
2021 : Fundamentals of Bayesian Inference »
Felipe Tobar -
2021 Tutorial: The Art of Gaussian Processes: Classical and Contemporary »
César Lincoln Mattos · Felipe Tobar -
2021 : Live Intro »
Felipe Tobar · César Lincoln Mattos -
2019 Poster: Band-Limited Gaussian Processes: The Sinc Kernel »
Felipe Tobar -
2017 Poster: Spectral Mixture Kernels for Multi-Output Gaussian Processes »
Gabriel Parra · Felipe Tobar -
2015 : Design of Covariance Functions using Inter-Domain Inducing Variables »
Felipe Tobar -
2015 Poster: Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels »
Felipe Tobar · Thang Bui · Richard Turner -
2015 Spotlight: Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels »
Felipe Tobar · Thang Bui · Richard Turner