English
Related papers

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

200 papers

A new (unadjusted) Langevin Monte Carlo (LMC) algorithm with improved rates in total variation and in Wasserstein distance is presented. All these are obtained in the context of sampling from a target distribution $\pi$ that has a density…

Statistics Theory · Mathematics 2019-10-18 Sotirios Sabanis , Ying Zhang

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

Acceleration is a celebrated cornerstone of convex optimization, enabling gradient-based algorithms to converge sublinearly in the condition number. A major open question is whether an analogous acceleration phenomenon is possible for…

Probability · Mathematics 2026-04-01 Jason M. Altschuler , Sinho Chewi , Matthew S. Zhang

We study Hamiltonian Monte Carlo (HMC) for sampling from a strongly logconcave density proportional to $e^{-f}$ where $f:\mathbb{R}^d \to \mathbb{R}$ is $\mu$-strongly convex and $L$-smooth (the condition number is $\kappa = L/\mu$). We…

Data Structures and Algorithms · Computer Science 2019-05-08 Zongchen Chen , Santosh S. Vempala

Cold-start exploration is a core challenge in large-scale recommender systems: new or data-sparse items must receive traffic to estimate value, but over-exploration harms users and wastes impressions. In practice, Thompson Sampling (TS) is…

Machine Learning · Computer Science 2026-02-03 Zhenyu Zhao , David Zhang , Ellie Zhao , Ehsan Saberian

We show that the gradient norm $\|\nabla f(x)\|$ for $x \sim \exp(-f(x))$, where $f$ is strongly convex and smooth, concentrates tightly around its mean. This removes a barrier in the prior state-of-the-art analysis for the well-studied…

Machine Learning · Computer Science 2020-06-16 Yin Tat Lee , Ruoqi Shen , Kevin Tian

Width expansion offers a practical route to reuse smaller causal-language-model checkpoints, but selecting a widened warm start is not solved by zero-step preservation alone. We study dense width growth as a candidate-selection problem over…

Artificial Intelligence · Computer Science 2026-04-07 Eren Unlu

Yang et al. (2023) recently showed how to use first-order gradient methods to solve general variational inequalities (VIs) under a limiting assumption that analytic solutions of specific subproblems are available. In this paper, we…

Machine Learning · Statistics 2024-08-06 Tatjana Chavdarova , Tong Yang , Matteo Pagliardini , Michael I. Jordan

We give algorithms for sampling several structured logconcave families to high accuracy. We further develop a reduction framework, inspired by proximal point methods in convex optimization, which bootstraps samplers for regularized…

Data Structures and Algorithms · Computer Science 2021-10-25 Yin Tat Lee , Ruoqi Shen , Kevin Tian

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

Sampling from multimodal distributions is a central challenge in Bayesian inference and machine learning. In light of hardness results for sampling -- classical MCMC methods, even with tempering, can suffer from exponential mixing times --…

Machine Learning · Statistics 2025-12-23 Holden Lee , Matheau Santana-Gijzen

We analyze Riemannian Hamiltonian Monte Carlo (RHMC) for sampling a polytope defined by $m$ inequalities in $\R^n$ endowed with the metric defined by the Hessian of a convex barrier function. The advantage of RHMC over Euclidean methods…

Data Structures and Algorithms · Computer Science 2023-04-20 Khashayar Gatmiry , Jonathan Kelner , Santosh S. Vempala

Inference for models with recursively defined likelihoods is computationally demanding, limiting scalability to large datasets. We propose a stabilised weighted subsampling methodology for accelerated inference based on an unbiased…

Methodology · Statistics 2026-05-14 Matias Quiroz , Aishwarya Bhaskaran , Zixuan Wang , Thomas Goodwin

Logarithmic Sobolev inequalities are a powerful way to estimate the rate of convergence of Markov chains and to derive concentration inequalities on distributions. We prove that the log-Sobolev constant of any isotropic logconcave density…

Probability · Mathematics 2017-12-06 Yin Tat Lee , Santosh S. Vempala

Shape constraints yield flexible middle grounds between fully nonparametric and fully parametric approaches to modeling distributions of data. The specific assumption of log-concavity is motivated by applications across economics, survival…

Methodology · Statistics 2024-04-16 Robin Dunn , Aditya Gangrade , Larry Wasserman , Aaditya Ramdas

Langevin diffusion processes and their discretizations are often used for sampling from a target density. The most convenient framework for assessing the quality of such a sampling scheme corresponds to smooth and strongly log-concave…

Probability · Mathematics 2018-12-27 Arnak S. Dalalyan , Lionel Riou-Durand

We propose a new method for linear second-order cone programs. It is based on the sequential quadratic programming framework for nonlinear programming. In contrast to interior point methods, it can capitalize on the warm-start capabilities…

Optimization and Control · Mathematics 2023-08-01 Xinyi Luo , Andreas Waechter

Physical parameters are often constrained from the data likelihoods using sampling methods. Changing some parameters can be much more computationally expensive (`slow') than changing other parameters (`fast parameters'). I describe a method…

Cosmology and Nongalactic Astrophysics · Physics 2013-06-19 Antony Lewis

We study the adaptation properties of the multivariate log-concave maximum likelihood estimator over three subclasses of log-concave densities. The first consists of densities with polyhedral support whose logarithms are piecewise affine.…

Statistics Theory · Mathematics 2019-10-21 Oliver Y. Feng , Adityanand Guntuboyina , Arlene K. H. Kim , Richard J. Samworth

Sampling from constrained statistical distributions is a fundamental task in various fields including Bayesian statistics, computational chemistry, and statistical physics. This article considers the cases where the constrained distribution…

Machine Learning · Computer Science 2025-10-28 Kijung Jeon , Michael Muehlebach , Molei Tao
‹ Prev 1 3 4 5 6 7 10 Next ›