English
Related papers

Related papers: Information theoretic limits of learning a sparse …

200 papers

We consider continuous-time sparse stochastic processes from which we have only a finite number of noisy/noiseless samples. Our goal is to estimate the noiseless samples (denoising) and the signal in-between (interpolation problem). By…

Machine Learning · Computer Science 2015-06-11 Arash Amini , Ulugbek S. Kamilov , Emrah Bostan , Michael Unser

We consider the estimation of an n-dimensional vector s from the noisy element-wise measurements of $\mathbf{s}\mathbf{s}^T$, a generic problem that arises in statistics and machine learning. We study a mismatched Bayesian inference…

Information Theory · Computer Science 2021-09-14 Farzad Pourkamali , Nicolas Macris

This note examines the behavior of generalization capabilities - as defined by out-of-sample mean squared error (MSE) - of Linear Gaussian (with a fixed design matrix) and Linear Least Squares regression. Particularly, we consider a…

Statistics Theory · Mathematics 2021-09-21 Karthik Duraisamy

We establish the convergence rates and asymptotic distributions of the common break change-point estimators, obtained by least squares and maximum likelihood in panel data models and compare their asymptotic variances. Our model assumptions…

Statistics Theory · Mathematics 2017-08-22 Monika Bhattacharjee , Moulinath Banerjee , George Michailidis

We study full Bayesian procedures for sparse linear regression when errors have a symmetric but otherwise unknown distribution. The unknown error distribution is endowed with a symmetrized Dirichlet process mixture of Gaussians. For the…

Statistics Theory · Mathematics 2019-03-26 Minwoo Chae , Lizhen Lin , David B. Dunson

We consider the estimation of a signal from the knowledge of its noisy linear random Gaussian projections, a problem relevant in compressed sensing, sparse superposition codes or code division multiple access just to cite few. There has…

Information Theory · Computer Science 2017-03-24 Jean Barbier , Mohamad Dia , Nicolas Macris , Florent Krzakala

We study the problem of recovering a hidden binary $k$-sparse $p$-dimensional vector $\beta$ from $n$ noisy linear observations $Y=X\beta+W$ where $X_{ij}$ are i.i.d. $\mathcal{N}(0,1)$ and $W_i$ are i.i.d. $\mathcal{N}(0,\sigma^2)$. A…

Statistics Theory · Mathematics 2019-03-13 Galen Reeves , Jiaming Xu , Ilias Zadik

Denoising diffusion models have spurred significant gains in density modeling and image generation, precipitating an industrial revolution in text-guided AI art generation. We introduce a new mathematical foundation for diffusion models…

Machine Learning · Computer Science 2023-02-09 Xianghao Kong , Rob Brekelmans , Greg Ver Steeg

We consider the task of estimating a low-rank matrix from non-linear and noisy observations. We prove a strong universality result showing that Bayes-optimal performances are characterized by an equivalent Gaussian model with an effective…

Machine Learning · Statistics 2024-03-08 Pierre Mergny , Justin Ko , Florent Krzakala , Lenka Zdeborová

We consider mean squared estimation with lookahead of a continuous-time signal corrupted by additive white Gaussian noise. We show that the mutual information rate function, i.e., the mutual information rate as function of the…

Information Theory · Computer Science 2016-11-18 Kartik Venkat , Tsachy Weissman , Yair Carmon , Shlomo Shamai

Inference and prediction under the sparsity assumption have been a hot research topic in recent years. However, in practice, the sparsity assumption is difficult to test, and more importantly can usually be violated. In this paper, to study…

Statistics Theory · Mathematics 2022-10-18 Yanmei Shi , Zhiruo Li , Qi Zhang

The minimum mean-squared error (MMSE) is one of the most popular criteria for Bayesian estimation. Conversely, the signal-to-noise ratio (SNR) is a typical performance criterion in communications, radar, and generally detection theory. In…

Information Theory · Computer Science 2016-10-12 Luca Rugini , Paolo Banelli

We consider a multivariate functional measurement error model $AX\approx B$. The errors in $[A,B]$ are uncorrelated, row-wise independent, and have equal (unknown) variances. We study the total least squares estimator of $X$, which, in the…

Probability · Mathematics 2016-07-14 Alexander Kukush , Yaroslav Tsaregorodtsev

We consider the problem of learning a coefficient vector $x_{0}$ in $R^{N}$ from noisy linear observations $y=Fx_{0}+w$ in $R^{M}$ in the high dimensional limit $M,N$ to infinity with $\alpha=M/N$ fixed. We provide a rigorous derivation of…

Machine Learning · Statistics 2020-02-12 Cédric Gerbelot , Alia Abbara , Florent Krzakala

Asymptotic expressions of the mutual information between any discrete input and the corresponding output of the scalar additive white Gaussian noise channel are presented in the limit as the signal-to-noise ratio (SNR) tends to infinity.…

Information Theory · Computer Science 2014-04-23 Alex Alvarado , Fredrik Brannstrom , Erik Agrell , Tobias Koch

An asymptotic technique is presented to characterize the bits/symbol achievable on a representative wireless link in a spatially distributed network with active interferers at correlated positions, N receive diversity branches, and linear…

Information Theory · Computer Science 2013-12-30 Siddhartan Govindasamy

In this work we study generalization guarantees for the metric learning problem, where the metric is induced by a neural network type embedding of the data. Specifically, we provide uniform generalization bounds for two regimes -- the…

Machine Learning · Computer Science 2021-02-09 Mark Kozdoba , Shie Mannor

A continuing mystery in understanding the empirical success of deep neural networks is their ability to achieve zero training error and generalize well, even when the training data is noisy and there are more parameters than data points. We…

Machine Learning · Computer Science 2019-09-10 Vidya Muthukumar , Kailas Vodrahalli , Vignesh Subramanian , Anant Sahai

This monograph presents a unified treatment of single- and multi-user problems in Shannon's information theory where we depart from the requirement that the error probability decays asymptotically in the blocklength. Instead, the error…

Information Theory · Computer Science 2015-04-13 Vincent Y. F. Tan

We study the problem of estimating a rank-1 additive deformation of a Gaussian tensor according to the \emph{maximum-likelihood estimator} (MLE). The analysis is carried out in the sparse setting, where the underlying signal has a support…

Information Theory · Computer Science 2021-01-26 Luca Corinzia , Paolo Penna , Wojciech Szpankowski , Joachim M. Buhmann