English
Related papers

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

200 papers

Deep Neural Networks for classification behave unpredictably when confronted with inputs not stemming from the training distribution. This motivates out-of-distribution detection (OOD) mechanisms. The usual lack of prior information on…

Machine Learning · Computer Science 2022-03-02 Konstantin Kirchheim , Tim Gonschorek , Frank Ortmeier

In this paper, we consider the problem of Gaussian approximation for the online linear regression task. We derive the corresponding rates for the setting of a constant learning rate and study the explicit dependence of the convergence rate…

Machine Learning · Statistics 2025-09-18 Marat Khusainov , Marina Sheshukova , Alain Durmus , Sergey Samsonov

Recently, the precise performance of the Generalized LASSO algorithm for recovering structured signals from compressed noisy measurements, obtained via i.i.d. Gaussian matrices, has been characterized. The analysis is based on a framework…

Information Theory · Computer Science 2015-03-26 Christos Thrampoulidis , Babak Hassibi

Gaussian graphical models are widely used to represent correlations among entities but remain vulnerable to data corruption. In this work, we introduce a modified trimmed-inner-product algorithm to robustly estimate the covariance in an…

Machine Learning · Computer Science 2023-09-19 Tong Yao , Shreyas Sundaram

In classification problems when multiples algorithms are applied to different benchmarks a difficult issue arises, i.e., how can we rank the algorithms? In machine learning it is common run the algorithms several times and then a statistic…

Machine Learning · Computer Science 2016-10-25 Andre G. C. Pacheco , Renato A. Krohling

We study the average-case version of the Orthogonal Vectors problem, in which one is given as input $n$ vectors from $\{0,1\}^d$ which are chosen randomly so that each coordinate is $1$ independently with probability $p$. Kane and Williams…

Data Structures and Algorithms · Computer Science 2024-10-31 Josh Alman , Alexandr Andoni , Hengjie Zhang

The stochastic gradient descent (SGD) algorithm is widely used for parameter estimation, especially for huge data sets and online learning. While this recursive algorithm is popular for computation and memory efficiency, quantifying…

Machine Learning · Statistics 2021-06-23 Wanrong Zhu , Xi Chen , Wei Biao Wu

We propose a second-order accurate method to estimate the eigenvectors of extremely large matrices thereby addressing a problem of relevance to statisticians working in the analysis of very large datasets. More specifically, we show that…

Numerical Analysis · Mathematics 2010-02-05 Noureddine El Karoui , Alexandre d'Aspremont

Covariance matrix plays a central role in multivariate statistical analysis. Significant advances have been made recently on developing both theory and methodology for estimating large covariance matrices. However, a minimax theory has yet…

Statistics Theory · Mathematics 2010-10-20 T. Tony Cai , Cun-Hui Zhang , Harrison H. Zhou

Stochastic gradient algorithms are more and more studied since they can deal efficiently and online with large samples in high dimensional spaces. In this paper, we first establish a Central Limit Theorem for these estimates as well as for…

Statistics Theory · Mathematics 2017-10-17 Antoine Godichon-Baggioni

This paper studies probabilistic rates of convergence for consensus+innovations type of algorithms in random, generic networks. For each node, we find a lower and also a family of upper bounds on the large deviations rate function, thus…

Information Theory · Computer Science 2022-08-11 Dragana Bajovic

A common data analysis task is the reduced-rank regression problem: $$\min_{\textrm{rank-}k \ X} \|AX-B\|,$$ where $A \in \mathbb{R}^{n \times c}$ and $B \in \mathbb{R}^{n \times d}$ are given large matrices and $\|\cdot\|$ is some norm.…

Data Structures and Algorithms · Computer Science 2021-07-02 Praneeth Kacham , David P. Woodruff

Dataset replication is a useful tool for assessing whether improvements in test accuracy on a specific benchmark correspond to improvements in models' ability to generalize reliably. In this work, we present unintuitive yet significant ways…

For an $N \times T$ random matrix $X(\beta)$ with weakly dependent uniformly sub-Gaussian entries $x_{it}(\beta)$ that may depend on a possibly infinite-dimensional parameter $\beta\in \mathbf{B}$, we obtain a uniform bound on its operator…

Econometrics · Economics 2025-12-17 Grigory Franguridi , Hyungsik Roger Moon

In this short note we address a gaussian property of normal vectors in random non-Hermitian matrices. The approach uses a simple geometric and comparison technique.

Probability · Mathematics 2016-04-19 Hoi H. Nguyen

This article provides an original understanding of the behavior of a class of graph-oriented semi-supervised learning algorithms in the limit of large and numerous data. It is demonstrated that the intuition at the root of these methods…

Machine Learning · Computer Science 2017-11-10 Xiaoyi Mai , Romain Couillet

Correlation functions involving products and ratios of half-integer powers of characteristic polynomials of random matrices from the Gaussian Orthogonal Ensemble (GOE) frequently arise in applications of Random Matrix Theory (RMT) to…

Mathematical Physics · Physics 2015-04-23 Yan V. Fyodorov , André Nock

We study online aggregation of the predictions of experts, and first show new second-order regret bounds in the standard setting, which are obtained via a version of the Prod algorithm (and also a version of the polynomially weighted…

Machine Learning · Statistics 2014-02-11 Pierre Gaillard , Gilles Stoltz , Tim Van Erven

Motivated by the Koml\'os conjecture in combinatorial discrepancy, we study the discrepancy of random matrices with $m$ rows and $n$ independent columns drawn from a bounded lattice random variable. It is known that for $n$ tending to…

Combinatorics · Mathematics 2018-10-19 Cole Franks , Michael Saks

Bayesian inference provides an attractive online-learning framework to analyze sequential data, and offers generalization guarantees which hold even with model mismatch and adversaries. Unfortunately, exact Bayesian inference is rarely…

Machine Learning · Statistics 2020-08-03 Badr-Eddine Chérief-Abdellatif , Pierre Alquier , Mohammad Emtiyaz Khan