English
Related papers

Related papers: Information theoretic limits of learning a sparse …

200 papers

We study the information-theoretic limits of exactly recovering the support of a sparse signal using noisy projections defined by various classes of measurement matrices. Our analysis is high-dimensional in nature, in which the number of…

Statistics Theory · Mathematics 2008-06-04 Wei Wang , Martin J. Wainwright , Kannan Ramchandran

We investigate the problem of representing information measures in terms of the moments of the underlying random variables. First, we derive polynomial approximations of the conditional expectation operator. We then apply these…

Information Theory · Computer Science 2021-09-03 Wael Alghamdi , Flavio P. Calmon

A new empirical Bayes approach to variable selection in the context of generalized linear models is developed. The proposed algorithm scales to situations in which the number of putative explanatory variables is very large, possibly much…

Methodology · Statistics 2021-06-29 Haim Bar , James Booth , Martin T. Wells

Multi-task learning models using Gaussian processes (GP) have been developed and successfully applied in various applications. The main difficulty with this approach is the computational cost of inference using the union of examples from…

Machine Learning · Computer Science 2012-11-29 Yuyang Wang , Roni Khardon

This paper investigates the statistical properties of non-linear transformations (NLT) of random variables, in order to establish useful tools for estimation and information theory. Specifically, the paper focuses on linear regression…

Information Theory · Computer Science 2013-05-13 Paolo Banelli

We introduce a simple time-triggered protocol to achieve communication-efficient non-Bayesian learning over a network. Specifically, we consider a scenario where a group of agents interact over a graph with the aim of discerning the true…

Systems and Control · Electrical Eng. & Systems 2019-09-05 Aritra Mitra , John A. Richards , Shreyas Sundaram

Bayesian inference is a widely used statistical method. The free energy and generalization loss, which are used to estimate the accuracy of Bayesian inference, are known to be small in singular models that do not have a unique optimal…

Statistics Theory · Mathematics 2020-12-16 Shuya Nagayasu , Sumio Watanabe

When training data is sparse, more domain knowledge must be incorporated into the learning algorithm in order to reduce the effective size of the hypothesis space. This paper builds on previous work in which knowledge about qualitative…

Machine Learning · Computer Science 2012-07-09 Eric E. Altendorf , Angelo C. Restificar , Thomas G. Dietterich

This paper provides a unified framework for analyzing tensor estimation problems that allow for nonlinear observations, heteroskedastic noise, and covariate information. We study a general class of high-dimensional models where each…

Information Theory · Computer Science 2025-06-10 Riccardo Rossetti , Galen Reeves

Sparse coding refers to the pursuit of the sparsest representation of a signal in a typically overcomplete dictionary. From a Bayesian perspective, sparse coding provides a Maximum a Posteriori (MAP) estimate of the unknown vector under a…

Signal Processing · Electrical Eng. & Systems 2019-09-04 Dror Simon , Jeremias Sulam , Yaniv Romano , Yue M. Lu , Michael Elad

The minimum mean-square error of the estimation of a signal where observed from the additive white Gaussian noise (WGN) channel's output, is analyzed. It is assumed that the channel input's signal is composed of a (normalized) sum of N…

Information Theory · Computer Science 2007-07-13 Jacob Binia

Generalised linear models for multi-class classification problems are one of the fundamental building blocks of modern machine learning tasks. In this manuscript, we characterise the learning of a mixture of $K$ Gaussians with generic means…

We consider a sparse linear regression model Y=X\beta^{*}+W where X has a Gaussian entries, W is the noise vector with mean zero Gaussian entries, and \beta^{*} is a binary vector with support size (sparsity) k. Using a novel conditional…

Machine Learning · Statistics 2019-09-26 David Gamarnik , Ilias Zadik

We consider Bayesian inference of signals with vector-valued entries. Extending concentration techniques from the mathematical physics of spin glasses, we show that the matrix-valued minimum mean-square error concentrates when the size of…

Information Theory · Computer Science 2019-07-17 Jean Barbier

The support recovery problem consists of determining a sparse subset of a set of variables that is relevant in generating a set of observations, and arises in a diverse range of settings such as compressive sensing, and subset selection in…

Information Theory · Computer Science 2016-08-31 Jonathan Scarlett , Volkan Cevher

The minimum mean square error of the estimation of a non Gaussian signal where observed from an additive white Gaussian noise channel's output, is analyzed. First, a quite general time-continuous channel model is assumed for which the…

Information Theory · Computer Science 2010-02-04 Jacob Binia

The generalization error of a learning algorithm refers to the discrepancy between the loss of a learning algorithm on training data and that on unseen testing data. Various information-theoretic bounds on the generalization error have been…

Information Theory · Computer Science 2025-06-24 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

We consider nonparametric testing in a non-asymptotic framework. Our statistical guarantees are exact in the sense that Type I and II errors are controlled for any finite sample size. Meanwhile, one proposed test is shown to achieve minimax…

Statistics Theory · Mathematics 2017-02-07 Yun Yang , Zuofeng Shang , Guang Cheng

In this paper, we study Sibson's $\alpha$-mutual information in the context of the additive Gaussian noise channel. While the classical case $\alpha = 1$ is well understood and admits deep connections to estimation-theoretic quantities,…

Information Theory · Computer Science 2026-04-14 Mohammad Milanian , Alex Dytso , Martina Cardone

We provide an asymptotic expansion of the maximal mean squared error (MSE) of the sample median to be attained on shrinking gross error neighborhoods about an ideal central distribution. More specifically, this expansion comes in powers of…

Statistics Theory · Mathematics 2010-06-02 Peter Ruckdeschel
‹ Prev 1 4 5 6 7 8 10 Next ›