English
Related papers

Related papers: Optimality of Maximum Likelihood for Log-Concave D…

200 papers

We consider the problem of predicting as well as the best linear combination of d given functions in least squares regression, and variants of this problem including constraints on the parameters of the linear combination. When the input…

Machine Learning · Statistics 2010-07-06 Jean-Yves Audibert , Olivier Catoni

We propose a likelihood ratio statistic for forming hypothesis tests and confidence intervals for a nonparametrically estimated univariate regression function, based on the shape restriction of concavity (alternatively, convexity). Dealing…

Statistics Theory · Mathematics 2018-09-11 Charles R. Doss

This paper proposes a novel non-parametric multidimensional convex regression estimator which is designed to be robust to adversarial perturbations in the empirical measure. We minimize over convex functions the maximum (over Wasserstein…

Statistics Theory · Mathematics 2020-07-28 Jose Blanchet , Peter W. Glynn , Jun Yan , Zhengqing Zhou

A very popular class of models for networks posits that each node is represented by a point in a continuous latent space, and that the probability of an edge between nodes is a decreasing function of the distance between them in this latent…

Statistics Theory · Mathematics 2025-01-07 Cosma Rohilla Shalizi , Dena Marie Asta

Optimal values and solutions of empirical approximations of stochastic optimization problems can be viewed as statistical estimators of their true values. From this perspective, it is important to understand the asymptotic behavior of these…

Optimization and Control · Mathematics 2025-07-01 Johannes Milz , Thomas M. Surowiec

We show that high-accuracy guarantees for log-concave sampling -- that is, iteration and query complexities which scale as $\mathrm{poly}\log(1/\delta)$, where $\delta$ is the desired target accuracy -- are achievable using stochastic…

Statistics Theory · Mathematics 2026-05-18 Fan Chen , Sinho Chewi , Constantinos Daskalakis , Alexander Rakhlin

Random effect models are popular statistical models for detecting and correcting spurious sample correlations due to hidden confounders in genome-wide gene expression data. In applications where some confounding factors are known,…

Methodology · Statistics 2021-11-08 Muhammad Ammar Malik , Tom Michoel

Denoising diffusions are a powerful method to generate approximate samples from high-dimensional data distributions. Recent results provide polynomial bounds on their convergence rate, assuming $L^2$-accurate scores. Until now, the tightest…

Machine Learning · Statistics 2024-03-07 Joe Benton , Valentin De Bortoli , Arnaud Doucet , George Deligiannidis

In this paper, we provide non-asymptotic upper bounds on the error of sampling from a target density using three schemes of discretized Langevin diffusions. The first scheme is the Langevin Monte Carlo (LMC) algorithm, the Euler…

Statistics Theory · Mathematics 2021-12-07 Arnak S. Dalalyan , Avetik Karagulyan , Lionel Riou-Durand

We resolve the min-max complexity of distributed stochastic convex optimization (up to a log factor) in the intermittent communication setting, where $M$ machines work in parallel over the course of $R$ rounds of communication to optimize…

Machine Learning · Computer Science 2021-08-06 Blake Woodworth , Brian Bullins , Ohad Shamir , Nathan Srebro

We study a likelihood ratio test for the location of the mode of a log-concave density. Our test is based on comparison of the log-likelihoods corresponding to the unconstrained maximum likelihood estimator of a log-concave density and the…

Statistics Theory · Mathematics 2018-06-05 Charles R. Doss , Jon A. Wellner

This paper presents a detailed theoretical analysis of the Langevin Monte Carlo sampling algorithm recently introduced in Durmus et al. (Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau, 2016)…

Methodology · Statistics 2017-05-26 Nicolas Brosse , Alain Durmus , Éric Moulines , Marcelo Pereyra

Stochastic convex optimization is one of the most well-studied models for learning in modern machine learning. Nevertheless, a central fundamental question in this setup remained unresolved: "How many data points must be observed so that…

Machine Learning · Computer Science 2023-11-10 Daniel Carmon , Roi Livni , Amir Yehudayoff

We study the fundamental problem of estimating the mean of a $d$-dimensional distribution with covariance $\Sigma \preccurlyeq \sigma^2 I_d$ given $n$ samples. When $d = 1$, \cite{catoni} showed an estimator with error $(1+o(1)) \cdot…

Statistics Theory · Mathematics 2024-02-20 Shivam Gupta , Samuel B. Hopkins , Eric Price

An elementary proof is provided of sharp bounds for the varentropy of random vectors with log-concave densities, as well as for deviations of the information content from its mean. These bounds significantly improve on the bounds obtained…

Probability · Mathematics 2019-03-06 Matthieu Fradelizi , Mokshay Madiman , Liyao Wang

The $\lambda$-exponential family generalizes the standard exponential family via a generalized convex duality motivated by optimal transport. It is the constant-curvature analogue of the exponential family from the information-geometric…

Statistics Theory · Mathematics 2025-05-07 Xiwei Tian , Ting-Kam Leonard Wong , Jiaowen Yang , Jun Zhang

A popular class of problem in statistics deals with estimating the support of a density from $n$ observations drawn at random from a $d$-dimensional distribution. The one-dimensional case reduces to estimating the end points of a univariate…

Statistics Theory · Mathematics 2018-04-27 Victor-Emmanuel Brunel , Jason M. Klusowski , Dana Yang

The sharpest known high probability generalization bounds for uniformly stable algorithms (Feldman, Vondr\'{a}k, 2018, 2019), (Bousquet, Klochkov, Zhivotovskiy, 2020) contain a generally inevitable sampling error term of order…

Machine Learning · Computer Science 2021-11-19 Yegor Klochkov , Nikita Zhivotovskiy

This paper investigates maximizers of the information divergence from an exponential family $E$. It is shown that the $rI$-projection of a maximizer $P$ to $E$ is a convex combination of $P$ and a probability measure $P_-$ with disjoint…

Information Theory · Computer Science 2014-06-18 Johannes Rauh

Overdamped Langevin dynamics are reversible stochastic differential equations which are commonly used to sample probability measures in high-dimensional spaces, such as the ones appearing in computational statistical physics and Bayesian…

Numerical Analysis · Mathematics 2025-02-10 Tony Lelièvre , Grigorios A. Pavliotis , Geneviève Robin , Régis Santet , Gabriel Stoltz
‹ Prev 1 3 4 5 6 7 10 Next ›