English
Related papers

Related papers: Dictionary Learning with Few Samples and Matrix Co…

200 papers

The recently established RPCA method provides us a convenient way to restore low-rank matrices from grossly corrupted observations. While elegant in theory and powerful in reality, RPCA may be not an ultimate solution to the low-rank matrix…

Methodology · Statistics 2014-07-17 Guangcan Liu , Ping Li

Consider $n$ complex random matrices $X_1,\ldots,X_n$ of size $d\times d$ sampled i.i.d. from a distribution with mean $E[X]=\mu$. While the concentration of averages of these matrices is well-studied, the concentration of other functions…

Probability · Mathematics 2020-03-16 Tarun Kathuria , Satyaki Mukherjee , Nikhil Srivastava

To learn (statistical) dependencies among random variables requires exponentially large sample size in the number of observed random variables if any arbitrary joint probability distribution can occur. We consider the case that sparse data…

Machine Learning · Computer Science 2007-05-23 Dominik Janzing , Daniel Herrmann

We study concentration inequalities for structured weighted sums of random data, including (i) tensor inner products and (ii) sequential matrix sums. We are interested in tail bounds and concentration inequalities for those structured…

Statistics Theory · Mathematics 2026-02-11 Chen Cheng , Rina Foygel Barber

This paper investigates graph clustering in the planted cluster model in the presence of {\em small clusters}. Traditional results dictate that for an algorithm to provably correctly recover the clusters, {\em all} clusters must be…

Machine Learning · Computer Science 2013-02-21 Nir Ailon , Yudong Chen , Xu Huan

As context windows in large language models continue to expand, it is essential to characterize how attention behaves at extreme sequence lengths. We introduce token-sample complexity: the rate at which attention computed on $n$ tokens…

Machine Learning · Computer Science 2026-03-24 Léa Bohbot , Cyril Letrouit , Gabriel Peyré , François-Xavier Vialard

We focus on \emph{row sampling} based approximations for matrix algorithms, in particular matrix multipication, sparse matrix reconstruction, and \math{\ell_2} regression. For \math{\matA\in\R^{m\times d}} (\math{m} points in \math{d\ll m}…

Data Structures and Algorithms · Computer Science 2011-03-29 Malik Magdon-Ismail

Given a large data matrix $A\in\mathbb{R}^{n\times n}$, we consider the problem of determining whether its entries are i.i.d. with some known marginal distribution $A_{ij}\sim P_0$, or instead $A$ contains a principal submatrix $A_{{\sf…

Computational Complexity · Computer Science 2015-02-24 Yash Deshpande , Andrea Montanari

Grammar compression is a general compression framework in which a string $T$ of length $N$ is represented as a context-free grammar of size $n$ whose language contains only $T$. In this paper, we focus on studying the limitations of…

Data Structures and Algorithms · Computer Science 2024-09-24 Rajat De , Dominik Kempa

Many modern tools in machine learning and signal processing, such as sparse dictionary learning, principal component analysis (PCA), non-negative matrix factorization (NMF), $K$-means clustering, etc., rely on the factorization of a matrix…

Machine Learning · Statistics 2015-04-10 Rémi Gribonval , Rodolphe Jenatton , Francis Bach , Martin Kleinsteuber , Matthias Seibert

In this paper we study the behaviour of the domination number of the Erd\H{o}s-R\'enyi random graph $\mathcal{G}(n,p)$. Extending a result of Wieland and Godbole we show that the domination number of $\mathcal{G}(n,p)$ is equal to one of…

Combinatorics · Mathematics 2015-03-17 Roman Glebov , Anita Liebenau , Tibor Szabó

We study the learnability of sums of independent integer random variables given a bound on the size of the union of their supports. For $\mathcal{A} \subset \mathbf{Z}_{+}$, a sum of independent random variables with collective support…

Data Structures and Algorithms · Computer Science 2020-11-13 Anindya De , Philip M. Long , Rocco A. Servedio

Analyzing probabilistic programs and randomized algorithms are classical problems in computer science. The first basic problem in the analysis of stochastic processes is to consider the expectation or mean, and another basic problem is to…

Programming Languages · Computer Science 2020-08-13 Jinyi Wang , Yican Sun , Hongfei Fu , Mingzhang Huang , Amir Kafshdar Goharshady , Krishnendu Chatterjee

Pseudospectral analysis serves as a powerful tool in matrix computation and the study of both linear and nonlinear dynamical systems. Among various numerical strategies, random sampling, especially in the form of rank-$1$ perturbations,…

Spectral Theory · Mathematics 2025-05-19 Kuo Gai , Bin Shi

We consider increasingly complex models of matrix denoising and dictionary learning in the Bayes-optimal setting, in the challenging regime where the matrices to infer have a rank growing linearly with the system size. This is in contrast…

Information Theory · Computer Science 2022-09-14 Jean Barbier , Nicolas Macris

We address the collective matrix completion problem of jointly recovering a collection of matrices with shared structure from partial (and potentially noisy) observations. To ensure well--posedness of the problem, we impose a joint low rank…

Machine Learning · Statistics 2015-04-09 Suriya Gunasekar , Makoto Yamada , Dawei Yin , Yi Chang

We show that for an $n\times n$ random matrix $A$ with independent uniformly anti-concentrated entries, such that $\mathbb{E} ||A||^2_{HS}\leq K n^2$, the smallest singular value $\sigma_n(A)$ of $A$ satisfies $$ P\left( \sigma_n(A)\leq…

Probability · Mathematics 2020-10-29 Galyna V. Livshyts , Konstantin Tikhomirov , Roman Vershynin

Let $\epsilon_1, \dotsc, \epsilon_n$ be i.i.d. Rademacher random variables taking values $\pm 1$ with probability $1/2$ each. Given an integer vector $\boldsymbol{a} = (a_1, \dotsc, a_n)$, its concentration probability is the quantity…

Combinatorics · Mathematics 2019-04-24 Asaf Ferber , Vishesh Jain , Kyle Luh , Wojciech Samotij

Matrix completion algorithms recover a low rank matrix from a small fraction of the entries, each entry contaminated with additive errors. In practice, the singular vectors and singular values of the low rank matrix play a pivotal role for…

Methodology · Statistics 2016-05-03 Juhee Cho , Donggyu Kim , Karl Rohe

We prove a matrix discrepancy bound that strengthens the famous Kadison-Singer result of Marcus, Spielman, and Srivastava. Consider any independent scalar random variables $\xi_1, \ldots, \xi_n$ with finite support, e.g. $\{ \pm 1 \}$ or…

Combinatorics · Mathematics 2020-08-05 Rasmus Kyng , Kyle Luh , Zhao Song