English
Related papers

Related papers: Universal compression of Gaussian sources with unk…

200 papers

We consider estimating the parameters of a Gaussian mixture density with a given number of components best representing a given set of weighted samples. We adopt a density interpretation of the samples by viewing them as a discrete Dirac…

Machine Learning · Statistics 2025-04-03 Daniel Frisch , Uwe D. Hanebeck

Consider the following problem: given two arbitrary densities $q_1,q_2$ and a sample-access to an unknown target density $p$, find which of the $q_i$'s is closer to $p$ in total variation. A remarkable result due to Yatracos shows that this…

Machine Learning · Computer Science 2025-12-16 Olivier Bousquet , Daniel Kane , Shay Moran

In this paper, source coding or data compression is viewed as a measurement problem. Given a measurement device with fewer states than the observable of a stochastic source, how can one capture the essential information? We propose modeling…

Chaotic Dynamics · Physics 2015-05-13 Nithin Nagaraj

Many applications require data processing to be performed on individual pieces of data which are of finite sizes, e.g., files in cloud storage units and packets in data networks. However, traditional universal compression solutions would…

Information Theory · Computer Science 2012-05-22 Ahmad Beirami , Mohsen Sardari , Faramarz Fekri

We investigate optimal subsampling for quantile regression. We derive the asymptotic distribution of a general subsampling estimator and then derive two versions of optimal subsampling probabilities. One version minimizes the trace of the…

Computation · Statistics 2020-01-29 HaiYing Wang , Yanyuan Ma

This paper studies the problem of estimating the covariance of a collection of vectors using only highly compressed measurements of each vector. An estimator based on back-projections of these compressive samples is proposed and analyzed. A…

Machine Learning · Statistics 2019-01-16 Martin Azizyan , Akshay Krishnamurthy , Aarti Singh

We consider a variant of the channel simulation problem with a single input and multiple outputs, where Alice observes a probability distribution $P$ from a set of prescribed probability distributions $\mathbb{\mathcal{P}}$, and sends a…

Information Theory · Computer Science 2021-09-07 Chak Fung Choi , Cheuk Ting Li

We study sequential probability assignment in the Gaussian setting, where the goal is to predict, or equivalently compress, a sequence of real-valued observations almost as well as the best Gaussian distribution with mean constrained to a…

Information Theory · Computer Science 2025-05-27 Jaouad Mourtada

Various optimality properties of universal sequence predictors based on Bayes-mixtures in general, and Solomonoff's prediction scheme in particular, will be studied. The probability of observing $x_t$ at time $t$, given past observations…

Machine Learning · Computer Science 2007-05-23 Marcus Hutter

In prefix coding over an infinite alphabet, methods that consider specific distributions generally consider those that decline more quickly than a power law (e.g., Golomb coding). Particular power-law distributions, however, model many…

Information Theory · Computer Science 2009-03-06 Michael B. Baer

We investigate Gaussian Universality for data distributions generated via diffusion models. By Gaussian Universality we mean that the test error of a generalized linear model $f(\mathbf{W})$ trained for a classification task on the…

Machine Learning · Statistics 2025-09-30 Reza Ghane , Anthony Bao , Danil Akhtiamov , Babak Hassibi

The goal in thinning is to summarize a dataset using a small set of representative points. Remarkably, sub-Gaussian thinning algorithms like Kernel Halving and Compress can match the quality of uniform subsampling while substantially…

Machine Learning · Statistics 2026-03-03 Annabelle Michael Carrell , Albert Gong , Abhishek Shetty , Raaz Dwivedi , Lester Mackey

We prove that $\tilde{\Theta}(k d^2 / \varepsilon^2)$ samples are necessary and sufficient for learning a mixture of $k$ Gaussians in $\mathbb{R}^d$, up to error $\varepsilon$ in total variation distance. This improves both the known upper…

Machine Learning · Computer Science 2020-07-23 Hassan Ashtiani , Shai Ben-David , Nick Harvey , Christopher Liaw , Abbas Mehrabian , Yaniv Plan

The Hessian method is widely applied in the global analysis of parton distribution functions (PDFs), which uses a set of orthogonal eigenvectors to give predictions of a physical observable. Its uncertainty is estimated based on the…

High Energy Physics - Phenomenology · Physics 2025-09-12 Wenxiao Zhan , Siqi Yang , Minghui Liu , Liang Han , Daniel Stump , C. -P. Yuan

Universal compression algorithms have been studied in the past for sequential change detection, where they have been used to estimate the post-change distribution in the modified version of the Cumulative Sum (CUSUM) Test. In this paper, we…

Information Theory · Computer Science 2021-12-15 Vikrant Malik , R. K. Bansal

Deep image compression performs better than conventional codecs, such as JPEG, on natural images. However, deep image compression is learning-based and encounters a problem: the compression performance deteriorates significantly for…

Image and Video Processing · Electrical Eng. & Systems 2022-11-03 Koki Tsubota , Hiroaki Akutsu , Kiyoharu Aizawa

In this work we study the estimation of the density of a totally positive random vector. Total positivity of the distribution of a random vector implies a strong form of positive dependence between its coordinates and, in particular, it…

Statistics Theory · Mathematics 2023-05-10 Ali Zartash , Elina Robeva

In this paper, we propose {\em distributed network compression via memory}. We consider two spatially separated sources with correlated unknown source parameters. We wish to study the universal compression of a sequence of length $n$ from…

Information Theory · Computer Science 2012-10-09 Ahmad Beirami , Faramarz Fekri

In the setting of a Gaussian channel without power constraints, proposed by Poltyrev, the codewords are points in an n-dimensional Euclidean space (an infinite constellation) and the tradeoff between their density and the error probability…

Information Theory · Computer Science 2013-02-28 Amir Ingber , Ram Zamir , Meir Feder

In the worst-case distributed source coding (DSC) problem of [1], the smaller cardinality of the support-set describing the correlation in informant data, may neither imply that fewer informant bits are required nor that fewer informants…

Information Theory · Computer Science 2009-07-13 Samar Agnihotri , Rajesh Venkatachalapathy