English
Related papers

Related papers: Black-box sampling for weakly smooth Langevin Mont…

200 papers

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

Bayesian max-margin models have shown superiority in various practical applications, such as text categorization, collaborative prediction, social network link prediction and crowdsourcing, and they conjoin the flexibility of Bayesian…

Machine Learning · Statistics 2016-10-19 Wenbo Hu , Jun Zhu , Bo Zhang

Hamiltonian Monte Carlo and underdamped Langevin Monte Carlo are state-of-the-art methods for taking samples from high-dimensional distributions with a differentiable density function. To generate samples, they numerically integrate…

Computation · Statistics 2025-05-20 Jakob Robnik , Reuben Cohn-Gordon , Uroš Seljak

We present a highly efficient proximal Markov chain Monte Carlo methodology to perform Bayesian computation in imaging problems. Similarly to previous proximal Monte Carlo approaches, the proposed method is derived from an approximation of…

Computation · Statistics 2020-03-20 Luis Vargas , Marcelo Pereyra , Konstantinos C. Zygalakis

Langevin MCMC gradient optimization is a class of increasingly popular methods for estimating a posterior distribution. This paper addresses the algorithm as applied in a decentralized setting, wherein data is distributed across a network…

Optimization and Control · Mathematics 2020-09-22 Vyacheslav Kungurtsev

In this work, we examine sampling problems with non-smooth potentials. We propose a novel Markov chain Monte Carlo algorithm for sampling from non-smooth potentials. We provide a non-asymptotical analysis of our algorithm and establish a…

Machine Learning · Computer Science 2022-02-11 Jiaming Liang , Yongxin Chen

Given a convex function $f\colon\mathbb{R}^{d}\to\mathbb{R}$, the problem of sampling from a distribution $\propto e^{-f(x)}$ is called log-concave sampling. This task has wide applications in machine learning, physics, statistics, etc. In…

Quantum Physics · Physics 2023-12-11 Andrew M. Childs , Tongyang Li , Jin-Peng Liu , Chunhao Wang , Ruizhe Zhang

For sampling from a log-concave density, we study implicit integrators resulting from $\theta$-method discretization of the overdamped Langevin diffusion stochastic differential equation. Theoretical and algorithmic properties of the…

Machine Learning · Statistics 2021-07-13 Liam Hodgkinson , Robert Salomone , Fred Roosta

Even in low dimensions, sampling from multi-modal distributions is challenging. We provide the first sampling algorithm for a broad class of distributions -- including all Gaussian mixtures -- with a query complexity that is polynomial in…

Computation · Statistics 2025-10-24 Adrien Vacher , Omar Chehab , Anna Korba

Recent work incorporating geometric ideas in Markov chain Monte Carlo is reviewed in order to highlight these advances and their possible application in a range of domains beyond Statistics. A full exposition of Markov chains and their use…

Computation · Statistics 2015-06-19 Samuel Livingstone , Mark Girolami

We propose a new discretization of the mirror-Langevin diffusion and give a crisp proof of its convergence. Our analysis uses relative convexity/smoothness and self-concordance, ideas which originated in convex optimization, together with a…

Statistics Theory · Mathematics 2021-10-26 Kwangjun Ahn , Sinho Chewi

Path integrals with complex actions are encountered for many physical systems ranging from spin- or mass-imbalanced atomic gases and graphene to quantum chromo-dynamics at finite density to the non-equilibrium evolution of quantum systems.…

High Energy Physics - Lattice · Physics 2022-09-01 Lukas Kades , Martin Gärttner , Thomas Gasenzer , Jan M. Pawlowski

Most works on federated learning (FL) focus on the most common frequentist formulation of learning whereby the goal is minimizing the global empirical loss. Frequentist learning, however, is known to be problematic in the regime of limited…

Information Theory · Computer Science 2022-06-13 Dongzhu Liu , Osvaldo Simeone

Gradient-based Monte Carlo sampling algorithms, like Langevin dynamics and Hamiltonian Monte Carlo, are important methods for Bayesian inference. In large-scale settings, full-gradients are not affordable and thus stochastic gradients…

Machine Learning · Computer Science 2019-06-25 Zhize Li , Tianyi Zhang , Shuyu Cheng , Jun Zhu , Jian Li

The Hamiltonian Monte Carlo (HMC) sampling algorithm exploits Hamiltonian dynamics to construct efficient Markov Chain Monte Carlo (MCMC), which has become increasingly popular in machine learning and statistics. Since HMC uses the gradient…

Machine Learning · Computer Science 2019-06-04 Minghao Gu , Shiliang Sun

There has been substantial interest in developing Markov chain Monte Carlo algorithms based on piecewise-deterministic Markov processes. However existing algorithms can only be used if the target distribution of interest is differentiable…

Statistics Theory · Mathematics 2021-11-12 Augustin Chevallier , Sam Power , Andi Q. Wang , Paul Fearnhead

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

Classically, the continuous-time Langevin diffusion converges exponentially fast to its stationary distribution $\pi$ under the sole assumption that $\pi$ satisfies a Poincar\'e inequality. Using this fact to provide guarantees for the…

Statistics Theory · Mathematics 2024-07-11 Sinho Chewi , Murat A. Erdogdu , Mufan Bill Li , Ruoqi Shen , Matthew Zhang

The Stochastic Gradient Langevin Dynamics (SGLD) are popularly used to approximate Bayesian posterior distributions in statistical learning procedures with large-scale data. As opposed to many usual Markov chain Monte Carlo (MCMC)…

Machine Learning · Statistics 2024-04-30 Kexin Jin , Chenguang Liu , Jonas Latz

Approximate Thompson sampling with Langevin Monte Carlo broadens its reach from Gaussian posterior sampling to encompass more general smooth posteriors. However, it still encounters scalability issues in high-dimensional problems when…

Machine Learning · Statistics 2024-06-24 Haoyang Zheng , Wei Deng , Christian Moya , Guang Lin
‹ Prev 1 3 4 5 6 7 10 Next ›