English
Related papers

Related papers: Shifted Composition III: Local Error Framework for…

200 papers

Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based…

Machine Learning · Computer Science 2025-08-25 Sebastian Sanokowski , Sepp Hochreiter , Sebastian Lehner

Score-matching generative models have proven successful at sampling from complex high-dimensional data distributions. In many applications, this distribution is believed to concentrate on a much lower $d$-dimensional manifold embedded into…

Machine Learning · Statistics 2025-04-25 Peter Potaptchik , Iskander Azangulov , George Deligiannidis

Non-parametric and distribution-free two-sample tests have been the foundation of many change point detection algorithms. However, randomness in the test statistic as a function of time makes them susceptible to false positives and…

Signal Processing · Electrical Eng. & Systems 2020-10-29 Kevin C. Cheng , Eric L. Miller , Michael C. Hughes , Shuchin Aeron

Designing experiments that systematically gather data from complex physical systems is central to accelerating scientific discovery. While Bayesian experimental design (BED) provides a principled, information-based framework that integrates…

Machine Learning · Computer Science 2026-01-26 Huchen Yang , Xinghao Dong , Jin-Long Wu

We revisit the classical problem of deriving convergence rates for the maximum likelihood estimator (MLE) in finite mixture models. The Wasserstein distance has become a standard loss function for the analysis of parameter estimation in…

Statistics Theory · Mathematics 2022-06-22 Tudor Manole , Nhat Ho

Notions of positive curvature have been shown to imply many remarkable properties for Markov processes, in terms, e.g., of regularization effects, functional inequalities, mixing time bounds and, more recently, the cutoff phenomenon. In…

Probability · Mathematics 2026-01-27 Francesco Pedrotti

Flow-based generative models enjoy certain advantages in computing the data generation and the likelihood, and have recently shown competitive empirical performance. Compared to the accumulating theoretical studies on related score-based…

Machine Learning · Statistics 2025-06-30 Xiuyuan Cheng , Jianfeng Lu , Yixin Tan , Yao Xie

Since pioneering work of Hinton et al., knowledge distillation based on Kullback-Leibler Divergence (KL-Div) has been predominant, and recently its variants have achieved compelling performance. However, KL-Div only compares probabilities…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Jiaming Lv , Haoyuan Yang , Peihua Li

Generative models have achieved remarkable success across a range of applications, yet their evaluation still lacks principled uncertainty quantification. In this paper, we develop a method for comparing how close different generative…

Machine Learning · Statistics 2025-10-24 Zijun Gao , Yan Sun , Han Su

A loss function measures the discrepancy between the true values and their estimated fits, for a given instance of data. In classification problems, a loss function is said to be proper if a minimizer of the expected loss is the true…

Information Theory · Computer Science 2020-01-03 Amichai Painsky , Gregory W. Wornell

Conformal prediction provides a powerful framework for constructing prediction intervals with finite-sample guarantees, yet its robustness under distribution shifts remains a significant challenge. This paper addresses this limitation by…

Machine Learning · Statistics 2025-05-20 Liviu Aolaritei , Zheyu Oliver Wang , Julie Zhu , Michael I. Jordan , Youssef Marzouk

We study concentration inequalities for the Kullback--Leibler (KL) divergence between the empirical distribution and the true distribution. Applying a recursion technique, we improve over the method of types bound uniformly in all regimes…

Information Theory · Computer Science 2019-10-22 Jay Mardia , Jiantao Jiao , Ervin Tánczos , Robert D. Nowak , Tsachy Weissman

Underdamped Langevin dynamics (ULD) is a widely-used sampler for Gibbs distributions $\pi\propto e^{-V}$, and is often empirically effective in high dimensions. However, existing non-asymptotic convergence guarantees for discretized ULD…

Machine Learning · Computer Science 2026-03-04 Shiyuan Zhang , Qiwei Di , Xuheng Li , Quanquan Gu

We show the $L^2$-Wasserstein contraction for the transition kernel of a discretised diffusion process, under a contractivity at infinity condition on the drift and a sufficiently high diffusivity requirement. This extends recent results…

Probability · Mathematics 2023-10-25 Linshan Liu , Mateusz B. Majka , Pierre Monmarché

We establish a sharp uniform-in-time error estimate for the Stochastic Gradient Langevin Dynamics (SGLD), which is a widely-used sampling algorithm. Under mild assumptions, we obtain a uniform-in-time $O(\eta^2)$ bound for the KL-divergence…

Probability · Mathematics 2025-03-20 Lei Li , Yuliang Wang

Orthogonal nonnegative matrix factorization (ONMF) has become a standard approach for clustering. As far as we know, most works on ONMF rely on the Frobenius norm to assess the quality of the approximation. This paper presents a new model…

Machine Learning · Statistics 2025-11-06 Jean Pacifique Nkurunziza , Fulgence Nahayo , Nicolas Gillis

This work considers the problem of sampling from a probability distribution known up to a normalization constant while satisfying a set of statistical constraints specified by the expected values of general nonlinear functions. This problem…

Machine Learning · Statistics 2025-01-08 Luiz F. O. Chamon , Mohammad Reza Karimi , Anna Korba

Stochastic reduced-order models are widely used to represent the effective dynamics of complex systems, but estimating their drift and diffusion coefficients from data remains challenging. Standard approaches often rely on short-time…

Machine Learning · Statistics 2026-04-28 Ludovico T. Giorgini

Hamiltonian Monte Carlo (HMC) algorithms are among the most widely used sampling methods in high dimensional settings, yet their convergence properties are poorly understood in divergences that quantify relative density mismatch, such as…

Machine Learning · Statistics 2026-01-15 Nawaf Bou-Rabee , Siddharth Mitra , Andre Wibisono

When we consider canonical averages for classical discrete systems, typically referred to as substitutional alloys, the map phi from many-body interatomic interactions to thermodynamic equilibrium configurations generally exhibits…

Statistical Mechanics · Physics 2026-05-12 Koretaka Yuge