English
Related papers

Related papers: High-dimensional Bayesian inference via the Unadju…

200 papers

We propose a general purpose Bayesian inference algorithm for expensive likelihoods, replacing the stochastic term in the Langevin equation with a deterministic density gradient term. The particle density is evaluated from the current…

Machine Learning · Statistics 2022-10-14 Richard D. P. Grumitt , Biwei Dai , Uros Seljak

Flexible Bayesian models are typically constructed using limits of large parametric models with a multitude of parameters that are often uninterpretable. In this article, we offer a novel alternative by constructing an exponentially tilted…

Methodology · Statistics 2023-03-20 Abhisek Chakraborty , Anirban Bhattacharya , Debdeep Pati

We study the task of efficiently sampling from a Gibbs distribution $d \pi^* = e^{-h} d {vol}_g$ over a Riemannian manifold $M$ via (geometric) Langevin MCMC; this algorithm involves computing exponential maps in random Gaussian directions…

Statistics Theory · Mathematics 2024-02-19 Xiang Cheng , Jingzhao Zhang , Suvrit Sra

We study the problem of sampling from a distribution $p^*(x) \propto \exp\left(-U(x)\right)$, where the function $U$ is $L$-smooth everywhere and $m$-strongly convex outside a ball of radius $R$, but potentially nonconvex inside this ball.…

The task of sampling from a high-dimensional distribution $\pi$ on $\R^d$ is a fundamental algorithmic problem with applications throughout statistics, engineering, and the sciences. Consider the Langevin diffusion on $\R^d$ \begin{align*}…

Statistics Theory · Mathematics 2025-11-18 Tian Shen , Zhonggen Su

The likelihood function is a fundamental component in Bayesian statistics. However, evaluating the likelihood of an observation is computationally intractable in many applications. In this paper, we propose a non-parametric approximation of…

Machine Learning · Computer Science 2019-10-24 Viet Anh Nguyen , Soroosh Shafieezadeh-Abadeh , Man-Chung Yue , Daniel Kuhn , Wolfram Wiesemann

A well-known first-order method for sampling from log-concave probability distributions is the Unadjusted Langevin Algorithm (ULA). This work proposes a new annealing step-size schedule for ULA, which allows to prove new convergence…

Statistics Theory · Mathematics 2020-07-03 Paul Rolland , Armin Eftekhari , Ali Kavis , Volkan Cevher

The Metropolis-adjusted Langevin algorithm (MALA) is a Metropolis-Hastings method for approximate sampling from continuous distributions. We derive upper bounds for the contraction rate in Kantorovich-Rubinstein-Wasserstein distance of the…

Probability · Mathematics 2014-01-17 Andreas Eberle

In this paper we propose tight upper and lower bounds for the Wasserstein distance between any two {{univariate continuous distributions}} with probability densities $p_1$ and $p_2$ having nested supports. These explicit bounds are…

Probability · Mathematics 2015-10-21 Christophe Ley , Gesine Reinert , Yvik Swan

This paper studies the Gaussian and bootstrap approximations for the probabilities of a non-degenerate U-statistic belonging to the hyperrectangles in $\mathbb{R}^d$ when the dimension $d$ is large. A two-step Gaussian approximation…

Statistics Theory · Mathematics 2017-07-11 Xiaohui Chen

In this paper, we provide new insights on the Unadjusted Langevin Algorithm. We show that this method can be formulated as a first order optimization algorithm of an objective functional defined on the Wasserstein space of order $2$. Using…

Computation · Statistics 2018-03-30 Alain Durmus , Szymon Majewski , Błażej Miasojedow

It is of significant interest in many applications to sample from a high-dimensional target distribution $\pi$ with the density $\pi(\text{d} x) \propto e^{-U(x)} (\text{d} x) $, based on the temporal discretization of the Langevin…

Numerical Analysis · Mathematics 2025-01-30 Chenxu Pang , Xiaojie Wang , Yue Wu

We study high-dimensional Bayesian linear regression with product priors. Using the nascent theory of non-linear large deviations (Chatterjee and Dembo,2016), we derive sufficient conditions for the leading-order correctness of the naive…

Statistics Theory · Mathematics 2021-04-27 Sumit Mukherjee , Subhabrata Sen

We derive normal approximation bounds in the Wasserstein distance for sums of weighted U-statistics, based on a general distance bound for functionals of independent random variables of arbitrary distributions. Those bounds are applied to…

Probability · Mathematics 2020-07-28 Nicolas Privault , Grzegorz Serafin

We examine the Langevin diffusion confined to a closed, convex domain $D\subset\mathbb{R}^d$, represented as a reflected stochastic differential equation. We introduce a sequence of penalized stochastic differential equations and prove that…

Probability · Mathematics 2026-01-22 Tarika Mane , Amine Boukardagha

We derive first-order (in the stepsize) bounds on the bias in Wasserstein distances of the invariant measure of stochastic gradient kinetic Langevin dynamics with minimal assumptions on the stochastic gradient noise. These bounds sharpen…

Computation · Statistics 2026-04-28 Daniel Paulin , Peter A. Whalley

The problem of efficiently generating random samples from high-dimensional and non-log-concave posterior measures arising from nonlinear regression problems is considered. Extending investigations from arXiv:2009.05298, local and global…

Statistics Theory · Mathematics 2023-04-18 Jan Bohr , Richard Nickl

This paper studies inference for the mean vector of a high-dimensional $U$-statistic. In the era of Big Data, the dimension $d$ of the $U$-statistic and the sample size $n$ of the observations tend to be both large, and the computation of…

Statistics Theory · Mathematics 2019-01-29 Xiaohui Chen , Kengo Kato

Being able to reliably assess not only the \emph{accuracy} but also the \emph{uncertainty} of models' predictions is an important endeavour in modern machine learning. Even if the model generating the data and labels is known, computing the…

Machine Learning · Computer Science 2023-09-12 Lucas Clarté , Bruno Loureiro , Florent Krzakala , Lenka Zdeborová

Bayesian solution of an inverse problem for indirect measurement $M = AU + {\mathcal{E}}$ is considered, where $U$ is a function on a domain of $R^d$. Here $A$ is a smoothing linear operator and $ {\mathcal{E}}$ is Gaussian white noise. The…

Probability · Mathematics 2009-01-28 Matti Lassas. Eero Saksman , Samuli Siltanen