English
Related papers

Related papers: Full large deviation principles for the largest ei…

200 papers

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

Heavy-tail phenomena in stochastic gradient descent (SGD) have been reported in several empirical studies. Experimental evidence in previous works suggests a strong interplay between the heaviness of the tails and generalization behavior of…

Machine Learning · Statistics 2023-01-31 Anant Raj , Lingjiong Zhu , Mert Gürbüzbalaban , Umut Şimşekli

We consider the following detection problem: given a realization of a symmetric matrix ${\mathbf{X}}$ of dimension $n$, distinguish between the hypothesis that all upper triangular variables are i.i.d. Gaussians variables with mean 0 and…

Statistics Theory · Mathematics 2014-11-25 Andrea Montanari , Daniel Reichman , Ofer Zeitouni

In this paper we provide explicit upper bounds on some distances between the (law of the) output of a random Gaussian NN and (the law of) a random Gaussian vector. Our results concern both shallow random Gaussian neural networks with…

We derive closed-form expressions for the Bayes optimal decision boundaries in binary classification of high dimensional overlapping Gaussian mixture model (GMM) data, and show how they depend on the eigenstructure of the class covariances,…

Machine Learning · Statistics 2024-05-29 Khen Cohen , Noam Levi , Yaron Oz

We compute the full order statistics of a one-dimensional gas of fermions in a harmonic trap at zero temperature, including its large deviation tails. The problem amounts to computing the probability distribution of the $k$th smallest…

Statistical Mechanics · Physics 2014-11-05 Isaac Pérez Castillo

Recent theoretical studies have shown that heavy-tails can emerge in stochastic optimization due to `multiplicative noise', even under surprisingly simple settings, such as linear regression with Gaussian data. While these studies have…

Machine Learning · Statistics 2025-05-06 Mert Gurbuzbalaban , Yuanhan Hu , Umut Simsekli , Kun Yuan , Lingjiong Zhu

The rate function for large deviations of the finite time Lyapunov exponent for the derived process in TM corresponding to a stochastic differential equation in M is related, via the Gartner-Ellis theorem, to the p-th moment Lyapunov…

Dynamical Systems · Mathematics 2025-07-23 Peter H Baxendale

We give a short, operator-theoretic proof of the asymptotic independence (including a first correction term) of the minimal and maximal eigenvalue of the n \times n Gaussian Unitary Ensemble in the large matrix limit n \to \infty. This is…

Probability · Mathematics 2010-06-01 Folkmar Bornemann

We study the cubic weakly nonlinear Schr\"odinger equation with randomized spatially quasi-periodic initial data in higher dimensions. Under a polynomial decay assumption in Fourier space, we establish a {\em Large Deviations Principle} for…

Probability · Mathematics 2026-04-21 Fei Xu , Yong Li

The tuning of stochastic gradient algorithms (SGAs) for optimization and sampling is often based on heuristics and trial-and-error rather than generalizable theory. We address this theory--practice gap by characterizing the large-sample…

Computation · Statistics 2023-07-21 Jeffrey Negrea , Jun Yang , Haoyue Feng , Daniel M. Roy , Jonathan H. Huggins

An important consideration for variable selection in interaction models is to design an appropriate penalty that respects hierarchy of the importance of the variables. A common theme is to include an interaction term only after the…

Statistics Theory · Mathematics 2016-03-31 Junlong Zhao , Chenlei Leng

We prove that an n by n random matrix G with independent entries is completely delocalized. Suppose the entries of G have zero means, variances uniformly bounded below, and a uniform tail decay of exponential type. Then with high…

Probability · Mathematics 2015-11-04 Mark Rudelson , Roman Vershynin

Gaussian processes (GPs) provide a probabilistic nonparametric representation of functions in regression, classification, and other problems. Unfortunately, exact learning with GPs is intractable for large datasets. A variety of approximate…

Machine Learning · Computer Science 2010-02-23 Yuan Qi , Ahmed H. Abdel-Gawad , Thomas P. Minka

This work deals with the isogeometric Galerkin discretization of the eigenvalue problem related to the Laplace operator subject to homogeneous Dirichlet boundary conditions on bounded intervals. This paper uses GLT theory to study the…

Numerical Analysis · Mathematics 2024-01-05 N. Lamsahel , A. El Akri , A. Ratnani

This paper deals with explicit upper and lower bounds for principal eigenvalues and the maximum principle associated to generalized Lane-Emden systems (GLE systems, for short). Regarding the bounds, we generalize the upper estimate of…

Analysis of PDEs · Mathematics 2024-10-10 Sabri Bahrouni , Edir Júnior Ferreira Leite , Gustavo Ferron Madeira

We establish maximal concentration bounds for the iterates generated by stochastic approximation algorithms with general step sizes, where the noise has a finite-state Markovian component plus a Martingale-difference component. When the…

Probability · Mathematics 2026-05-21 Shubhada Agrawal , Siva Theja Maguluri , Martin Zubeldia

We provide optimal lower bounds for two well-known parameter estimation (also known as statistical estimation) tasks in high dimensions with approximate differential privacy. First, we prove that for any $\alpha \le O(1)$, estimating the…

Statistics Theory · Mathematics 2024-01-05 Shyam Narayanan

The largest eigenvalue of random tensors is an important feature of systems involving disorder, equivalent to the ground state energy of glassy systems or to the injective norm of quantum states. For symmetric Gaussian random tensors of…

High Energy Physics - Theory · Physics 2024-12-16 Nicolas Delporte , Naoki Sasakura

We prove a local law and eigenvector delocalization for general Wigner-type matrices. Our methods allow us to get the best possible interval length and optimal eigenvector delocalization in the dense case, and the first results of such kind…

Probability · Mathematics 2019-04-12 Ioana Dumitriu , Yizhe Zhu