English
Related papers

Related papers: Faster logconcave sampling from a cold start in hi…

200 papers

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

We propose a novel warmstarting method for primal-dual interior point methods based on a smoothing operator that generates a starting point on the central path from the previous optimum. Compared to traditional approaches that prioritize…

Optimization and Control · Mathematics 2025-12-02 Yuwen Chen , Paul Goulart , Colin Jones

In this article we consider sampling from log concave distributions in Hamiltonian setting, without assuming that the objective gradient is globally Lipschitz. We propose two algorithms based on monotone polygonal (tamed) Euler schemes, to…

Probability · Mathematics 2023-01-20 Tim Johnston , Iosif Lytras , Sotirios Sabanis

We consider the inverse acoustic obstacle problem for sound-soft star-shaped obstacles in two dimensions wherein the boundary of the obstacle is determined from measurements of the scattered field at a collection of receivers outside the…

Numerical Analysis · Mathematics 2023-08-04 Mo Zhou , Jiequn Han , Manas Rachh , Carlos Borges

A conditional sampling oracle for a probability distribution D returns samples from the conditional distribution of D restricted to a specified subset of the domain. A recent line of work (Chakraborty et al. 2013 and Cannone et al. 2014)…

Data Structures and Algorithms · Computer Science 2016-08-18 Themistoklis Gouleakis , Christos Tzamos , Manolis Zampetakis

In this paper, we examine the problem of sampling from log-concave distributions with (possibly) superlinear gradient growth under kinetic (underdamped) Langevin algorithms. Using a carefully tailored taming scheme, we propose two novel…

Probability · Mathematics 2025-12-10 Iosif Lytras , Panayotis Mertikopoulos

In this paper, we study the problem of sampling from log-concave distributions supported on convex, compact sets, with a particular focus on the randomized midpoint discretization of both vanilla and kinetic Langevin diffusions in this…

Machine Learning · Statistics 2025-05-27 Yifeng Yu , Lu Yu

In this paper, we study the problem of sampling from a given probability density function that is known to be smooth and strongly log-concave. We analyze several methods of approximate sampling based on discretizations of the (highly…

Statistics Theory · Mathematics 2024-02-26 Arnak S. Dalalyan , Avetik G. Karagulyan

We study the proximal sampler of Lee, Shen, and Tian (2021) and obtain new convergence guarantees under weaker assumptions than strong log-concavity: namely, our results hold for (1) weakly log-concave targets, and (2) targets satisfying…

Statistics Theory · Mathematics 2022-02-15 Yongxin Chen , Sinho Chewi , Adil Salim , Andre Wibisono

In this paper, we revisit the recently established theoretical guarantees for the convergence of the Langevin Monte Carlo algorithm of sampling from a smooth and (strongly) log-concave density. We improve the existing results when the…

Statistics Theory · Mathematics 2017-07-31 Arnak S. Dalalyan

Sampling from probability distributions of the form $\sigma \propto e^{-\beta V}$, where $V$ is a continuous potential, is a fundamental task across physics, chemistry, biology, computer science, and statistics. However, when $V$ is…

Quantum Physics · Physics 2026-02-24 Jiaqi Leng , Zhiyan Ding , Zherui Chen , Lin Lin

The estimation of a log-concave density on $\mathbb{R}$ is a canonical problem in the area of shape-constrained nonparametric inference. We present a Bayesian nonparametric approach to this problem based on an exponentiated Dirichlet…

Statistics Theory · Mathematics 2020-07-14 Ester Mariucci , Kolyan Ray , Botond Szabo

We present algorithms for diffusion model sampling which obtain $\delta$-error in $\mathrm{polylog}(1/\delta)$ steps, given access to $\widetilde O(\delta)$-accurate score estimates in $L^2$. This is an exponential improvement over all…

Machine Learning · Computer Science 2026-04-28 Fan Chen , Sinho Chewi , Constantinos Daskalakis , Alexander Rakhlin

Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample from unnormalized densities by leveraging the momentum of a particle moving in a potential well. We provide a novel analysis of ULMC, motivated by two central questions:…

Statistics Theory · Mathematics 2023-02-17 Matthew Zhang , Sinho Chewi , Mufan Bill Li , Krishnakumar Balasubramanian , Murat A. Erdogdu

We propose a new method for local distance metric learning based on sample similarity as side information. These local metrics, which utilize conical combinations of metric weight matrices, are learned from the pooled spatial…

Machine Learning · Computer Science 2019-02-25 YInjie Huang , Cong Li , Michael Georgiopoulos , Georgios C. Anagnostopoulos

Sampling from various kinds of distributions is an issue of paramount importance in statistics since it is often the key ingredient for constructing estimators, test procedures or confidence intervals. In many situations, the exact sampling…

Computation · Statistics 2016-12-06 Arnak S. Dalalyan

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.…

Sampling is a fundamental and arguably very important task with numerous applications in Machine Learning. One approach to sample from a high dimensional distribution $e^{-f}$ for some function $f$ is the Langevin Algorithm (LA). Recently,…

Machine Learning · Computer Science 2020-12-08 Xiao Wang , Qi Lei , Ioannis Panageas

We study sampling problems associated with non-convex potentials that meanwhile lack smoothness. In particular, we consider target distributions that satisfy either logarithmic-Sobolev inequality or Poincar\'e inequality. Rather than…

Machine Learning · Computer Science 2023-02-21 Jiaming Liang , Yongxin Chen

Cosine similarity is the common choice for measuring the distance between the feature representations in contrastive visual-textual alignment learning. However, empirically a learnable softmax temperature parameter is required when learning…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Zhun Sun