English
Related papers

Related papers: Average-Case Matrix Discrepancy: Asymptotics and O…

200 papers

This work demonstrates a methodology for using deep learning to discover simple, practical criteria for classifying matrices based on abstract algebraic properties. By combining a high-performance neural network with explainable AI (XAI)…

Machine Learning · Computer Science 2025-07-31 Leandro Farina , Sergey Korotov

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

For real symmetric matrices that are accessible only through matrix vector products, we present Monte Carlo estimators for computing the diagonal elements. Our probabilistic bounds for normwise absolute and relative errors apply to Monte…

Numerical Analysis · Mathematics 2022-03-18 Eric Hallman , Ilse C. F. Ipsen , Arvind Saibaba

We estimate the norms of standard Gaussian random Toeplitz and circulant matrices and their inverses, mostly by means of combining some basic techniques of linear algebra. In the case of circulant matrices we obtain sharp probabilistic…

Numerical Analysis · Mathematics 2013-11-18 Victor Y. Pan , Guolian Qian

We study the problem of residual error estimation for matrix and vector norms using a linear sketch. Such estimates can be used, for example, to quickly assess how useful a more expensive low-rank approximation computation will be. The…

Data Structures and Algorithms · Computer Science 2024-08-19 Yi Li , Honghao Lin , David P. Woodruff

The Gaussian graphical model, a popular paradigm for studying relationship among variables in a wide range of applications, has attracted great attention in recent years. This paper considers a fundamental question: When is it possible to…

Statistics Theory · Mathematics 2015-06-04 Zhao Ren , Tingni Sun , Cun-Hui Zhang , Harrison H. Zhou

We analyze the macroscale behavior of random lower (and therefore upper) triangular matrices with entries drawn iid from a distribution with nonzero mean and finite variance. We show that such a matrix behaves like a probabilistic version…

Probability · Mathematics 2021-04-07 J. E. Pascoe , Tapesh Yadav

Modern large-scale statistical models require to estimate thousands to millions of parameters. This is often accomplished by iterative algorithms such as gradient descent, projected gradient descent or their accelerated versions. What are…

Machine Learning · Statistics 2020-03-04 Michael Celentano , Andrea Montanari , Yuchen Wu

The problem of identifying change points in high-dimensional Gaussian graphical models (GGMs) in an online fashion is of interest, due to new applications in biology, economics and social sciences. The offline version of the problem, where…

Statistics Theory · Mathematics 2020-03-18 Hossein Keshavarz , George Michailidis

Randomized algorithms are overwhelming methods for low-rank approximation that can alleviate the computational expenditure with great reliability compared to deterministic algorithms. A crucial thought is generating a standard Gaussian…

Computation · Statistics 2025-06-05 Dandan Jiang , Bo Fu , Weiwei Xu

A recent approach to the Beck-Fiala conjecture, a fundamental problem in combinatorics, has been to understand when random integer matrices have constant discrepancy. We give a complete answer to this question for two natural models:…

Probability · Mathematics 2021-08-17 Dylan J. Altschuler , Jonathan Niles-Weed

We consider a variant of online convex optimization in which both the instances (input vectors) and the comparator (weight vector) are unconstrained. We exploit a natural scale invariance symmetry in our unconstrained setting: the…

Machine Learning · Computer Science 2017-08-24 Wojciech Kotłowski

We prove nonasymptotic matrix concentration inequalities for the spectral norm of (sub)gaussian random matrices with centered independent entries that capture fluctuations at the Tracy-Widom scale. This considerably improves previous bounds…

Probability · Mathematics 2025-03-21 Tatiana Brailovskaya , Ramon van Handel

Positive semi-definite matrices commonly occur as normal matrices of least squares problems in statistics or as kernel matrices in machine learning and approximation theory. They are typically large and dense. Thus algorithms to solve…

Numerical Analysis · Mathematics 2020-12-01 Markus Hegland , Frank deHoog

For two matroids $\mathcal{M}_1$ and $\mathcal{M}_2$ defined on the same ground set $E$, the online matroid intersection problem is to design an algorithm that constructs a large common independent set in an online fashion. The algorithm is…

Data Structures and Algorithms · Computer Science 2018-02-20 Guru Guruganesh , Sahil Singla

Variational algorithms have gained prominence over the past two decades as a scalable computational environment for Bayesian inference. In this article, we explore tools from the dynamical systems literature to study convergence of…

Dynamical Systems · Mathematics 2020-12-02 Sean Plummer , Debdeep Pati , Anirban Bhattacharya

In this work, we study the generalization capability of algorithms from an information-theoretic perspective. It has been shown that the expected generalization error of an algorithm is bounded from above by a function of the relative…

Information Theory · Computer Science 2021-10-27 Borja Rodríguez-Gálvez , Germán Bassi , Mikael Skoglund

The dynamic matrix inverse problem is to maintain the inverse of a matrix undergoing element and column updates. It is the main subroutine behind the best algorithms for many dynamic problems whose complexity is not yet well-understood,…

Data Structures and Algorithms · Computer Science 2019-05-14 Jan van den Brand , Danupon Nanongkai , Thatchaphol Saranurak

We study two one-parameter families of point processes connected to random matrices: the Sine_beta and Sch_tau processes. The first one is the bulk point process limit for the Gaussian beta-ensemble. For beta=1, 2 and 4 it gives the limit…

Probability · Mathematics 2013-11-19 Diane Holcomb , Benedek Valkó

We reconsider randomized algorithms for the low-rank approximation of symmetric positive semi-definite (SPSD) matrices such as Laplacian and kernel matrices that arise in data analysis and machine learning applications. Our main results…

Machine Learning · Computer Science 2013-06-05 Alex Gittens , Michael W. Mahoney