English
Related papers

Related papers: Sharp Matrix Empirical Bernstein Inequalities

200 papers

It is arguably believed that flatter minima can generalize better. However, it has been pointed out that the usual definitions of sharpness, which consider either the maxima or the integral of loss over a $\delta$ ball of parameters around…

Machine Learning · Computer Science 2021-01-11 Mingyang Yi , Huishuai Zhang , Wei Chen , Zhi-Ming Ma , Tie-Yan Liu

We prove a comparison theorem on the first Neumann eigenvalue on Bakry-Emery manifolds. Examples are constructed to illustrate the sharpness of the result. A linear explicit lower bound is also proved. We also discuss the asymptotic…

Analysis of PDEs · Mathematics 2011-11-22 Ben Andrews , Lei Ni

The Kochen-Specker theorem, Bell inequalities, and several other tests that were designed to rule out hidden-variable theories, assume the existence of observables having infinitely sharp eigenvalues. A paradigmatic example is spin-1/2. It…

Quantum Physics · Physics 2014-10-03 F. De Zela

We develop a theoretical approach to compute the conditioned spectral density of $N \times N$ non-invariant random matrices in the limit $N \rightarrow \infty$. This large deviation observable, defined as the eigenvalue distribution…

Disordered Systems and Neural Networks · Physics 2018-08-15 Isaac Pérez Castillo , Fernando L. Metz

Pseudo-hermitian matrices are matrices hermitian with respect to an indefinite metric. They can be thought of as the truncation of pseudo-hermitian operators, defined over some Krein space, together with the associated metric, to a finite…

Mathematical Physics · Physics 2022-02-03 Joshua Feinberg , Roman Riser

This paper investigates the supervised learning problem with observations drawn from certain general stationary stochastic processes. Here by \emph{general}, we mean that many stationary stochastic processes can be included. We show that…

Machine Learning · Statistics 2016-05-11 Hanyuan Hang , Yunlong Feng , Ingo Steinwart , Johan A. K. Suykens

The question of optimally approximating an arbitrary probability measure in the Wasserstein distance by a discrete one with uniform weights is considered. Estimates are obtained for the optimal approximation distance, with an explicit rate…

Probability · Mathematics 2026-04-14 Benjamin Seeger

Consider a sequence (indexed by n) of Markov chains Z^n in R^d characterized by transition kernels that approximately (in n) depend only on the rescaled state n^{-1} Z^n. Subject to a smoothness condition, such a family can be closely…

Probability · Mathematics 2009-08-17 Kamil Szczegot

We develop several methods, based on the geometric relationship between the eigenspaces of a matrix and its adjoint, for determining whether a square matrix having distinct eigenvalues is unitarily equivalent to a complex symmetric matrix.…

Functional Analysis · Mathematics 2010-03-16 Stephan Ramon Garcia , Levon Balayan

We establish bounds on the spectral radii for a large class of sparse random matrices, which includes the adjacency matrices of inhomogeneous Erd\H{o}s-R\'enyi graphs. Our error bounds are sharp for a large class of sparse random matrices.…

Probability · Mathematics 2021-01-25 Florent Benaych-Georges , Charles Bordenave , Antti Knowles

This article establishes cutoff convergence or abrupt convergence of three statistical quantities for multivariate (Hurwitz) stable geometric Brownian motion: the autocorrelation function, the Wasserstein distance between the current state…

Probability · Mathematics 2025-06-30 G. Barrera , M. A. Högele , J. C. Pardo

In the paper, by establishing the monotonicity of some functions involving the sine and cosine functions, the authors provide concise proofs of some known inequalities and find some new sharp inequalities involving the Seiffert,…

Classical Analysis and ODEs · Mathematics 2013-01-29 Wei-Dong Jiang , Feng Qi

This paper establishes sharp dimension-free concentration inequalities and expectation bounds for the deviation of the sum of simple random tensors from its expectation. As part of our analysis, we use generic chaining techniques to obtain…

Probability · Mathematics 2025-09-30 Omar Al-Ghattas , Jiaheng Chen , Daniel Sanz-Alonso

In this paper we derive sharp lower and upper bounds for the covariance of two bounded random variables when knowledge about their expected values, variances or both is available. When only the expected values are known, our result can be…

Probability · Mathematics 2021-06-21 Ola Hössjer , Arvid Sjölander

We give sharp, uniform estimates for the probability that the empirical distribution function for n uniform-[0,1] random variables stays to one side of a given line.

Probability · Mathematics 2008-05-02 Kevin Ford

Matrix concentration inequalities provide information about the probability that a random matrix is close to its expectation with respect to the $l_2$ operator norm. This paper uses semigroup methods to derive sharp nonlinear matrix…

Probability · Mathematics 2021-01-08 De Huang , Joel A. Tropp

Random geometric graphs result from taking $n$ uniformly distributed points in the unit cube, $[0,1]^d$, and connecting two points if their Euclidean distance is at most $r$, for some prescribed $r$. We show that monotone properties for…

Probability · Mathematics 2007-05-23 Ashish Goel , Sanatan Rai , Bhaskar Krishnamachari

In this review we summarise recent results for the complex eigenvalues and singular values of finite products of finite size random matrices, their correlation functions and asymptotic limits. The matrices in the product are taken from…

Mathematical Physics · Physics 2015-10-28 Gernot Akemann , Jesper R. Ipsen

The asymptotic behaviour of empirical measures has been studied extensively. In this paper, we consider empirical measures of given subordinated processes on complete (not necessarily compact) and connected Riemannian manifolds with…

Probability · Mathematics 2022-08-17 Huaiqian Li , Bingyao Wu

A concentration result for quadratic form of independent subgaussian random variables is derived. If the moments of the random variables satisfy a "Bernstein condition", then the variance term of the Hanson-Wright inequality can be…

Statistics Theory · Mathematics 2019-01-28 Pierre C Bellec