English
Related papers

Related papers: Fast parallel sampling under isoperimetry

200 papers

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 develop parallel algorithms for simulating zeroth-order (aka gradient-free) Metropolis Markov chains based on the Picard map. For Random Walk Metropolis Markov chains targeting log-concave distributions $\pi$ on $\mathbb{R}^d$, our…

Computation · Statistics 2026-04-10 Sebastiano Grazzi , Giacomo Zanella

We study Langevin-type algorithms for sampling from Gibbs distributions such that the potentials are dissipative and their weak gradients have finite moduli of continuity not necessarily convergent to zero. Our main result is a…

Statistics Theory · Mathematics 2024-03-01 Shogo Nakakita

Diffusion models over discrete spaces have recently shown striking empirical success, yet their theoretical foundations remain incomplete. In this paper, we study the sampling efficiency of score-based discrete diffusion models under a…

Machine Learning · Computer Science 2026-02-17 Daniil Dmitriev , Zhihan Huang , Yuting Wei

Understanding the dimension dependency of computational complexity in high-dimensional sampling problem is a fundamental problem, both from a practical and theoretical perspective. Compared with samplers with unbiased stationary…

Machine Learning · Computer Science 2024-03-12 Xunpeng Huang , Hanze Dong , Difan Zou , Tong Zhang

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.…

We study the approximation of arbitrary distributions $P$ on $d$-dimensional space by distributions with log-concave density. Approximation means minimizing a Kullback--Leibler-type functional. We show that such an approximation exists if…

Statistics Theory · Mathematics 2011-10-17 Lutz Duembgen , Richard Samworth , Dominic Schuhmacher

We provide a new convergence analysis of stochastic gradient Langevin dynamics (SGLD) for sampling from a class of distributions that can be non-log-concave. At the core of our approach is a novel conductance analysis of SGLD using an…

Machine Learning · Computer Science 2021-02-24 Difan Zou , Pan Xu , Quanquan Gu

We present a faster algorithm to generate a warm start for sampling an arbitrary logconcave density specified by an evaluation oracle, leading to the first sub-cubic sampling algorithms for inputs in (near-)isotropic position. A long line…

Data Structures and Algorithms · Computer Science 2025-05-06 Yunbum Kook , Santosh S. Vempala

In many problems in data mining and machine learning, data items that need to be clustered or classified are not points in a high-dimensional space, but are distributions (points on a high dimensional simplex). For distributions, natural…

Data Structures and Algorithms · Computer Science 2007-07-13 Sudipto Guha , Andrew McGregor , Suresh Venkatasubramanian

We study the problem of sampling from a distribution $\target$ using the Langevin Monte Carlo algorithm and provide rate of convergences for this algorithm in terms of Wasserstein distance of order $2$. Our result holds as long as the…

Computation · Statistics 2016-07-04 Thomas Bonis

Common assumptions, like linear or RKHS models, and Gaussian or log-concave posteriors over the models, do not explain practical success of RL across a wider range of distributions and models. Thus, we study how to design RL algorithms with…

Machine Learning · Computer Science 2025-02-06 Emilio Jorge , Christos Dimitrakakis , Debabrota Basu

We present a new random walk for uniformly sampling high-dimensional convex bodies. It achieves state-of-the-art runtime complexity with stronger guarantees on the output than previously known, namely in R\'enyi divergence (which implies…

Data Structures and Algorithms · Computer Science 2026-03-23 Yunbum Kook , Santosh S. Vempala , Matthew S. Zhang

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, the canonical Euler Maruyama discretization of the Langevin diffusion process, referred as Unadjusted Langevin Algorithm (ULA),…

Computation · Statistics 2021-07-28 Dao Nguyen , Xin Dang , Yixin Chen

The main goal of distribution network (DN) expansion planning is essentially to achieve minimal investment constrained with specified reliability requirements. The reliability-constrained distribution network planning (RcDNP) problem can be…

Systems and Control · Electrical Eng. & Systems 2023-03-10 Yaqi Sun , Wenchuan Wu , Yi Lin , Hai Huang , Hao Chen

In this paper, we propose a new numerical method for the underdamped Langevin diffusion (ULD) and present a non-asymptotic analysis of its sampling error in the 2-Wasserstein distance when the $d$-dimensional target distribution…

Machine Learning · Statistics 2025-08-25 Maximilian Scott , Dáire O'Kane , Andraž Jelinčič , James Foster

Uniform sampling over a convex body is a fundamental algorithmic problem, yet the convergence in KL or R\'enyi divergence of most samplers remains poorly understood. In this work, we propose a constrained proximal sampler, a principled and…

Data Structures and Algorithms · Computer Science 2024-07-19 Yunbum Kook , Matthew S. Zhang

Motivated by applications to deep learning which often fail standard Lipschitz smoothness requirements, we examine the problem of sampling from distributions that are not log-concave and are only weakly dissipative, with log-gradients…

Machine Learning · Statistics 2024-05-29 Iosif Lytras , Panayotis Mertikopoulos

Diffusion models have become a leading method for generative modeling of both image and scientific data. As these models are costly to train and \emph{evaluate}, reducing the inference cost for diffusion models remains a major goal.…

Machine Learning · Computer Science 2025-12-01 Haoxuan Chen , Yinuo Ren , Lexing Ying , Grant M. Rotskoff

We extend the Langevin Monte Carlo (LMC) algorithm to compactly supported measures via a projection step, akin to projected Stochastic Gradient Descent (SGD). We show that (projected) LMC allows to sample in polynomial time from a…

Probability · Mathematics 2016-08-08 Sébastien Bubeck , Ronen Eldan , Joseph Lehec