English
Related papers

Related papers: Online Sampling from Log-Concave Distributions

200 papers

We present quantum algorithms for sampling from non-logconcave probability distributions in the form of $\pi(x) \propto \exp(-\beta f(x))$. Here, $f$ can be written as a finite sum $f(x):= \frac{1}{N}\sum_{k=1}^N f_k(x)$. Our approach is…

Quantum Physics · Physics 2023-10-18 Guneykan Ozgul , Xiantao Li , Mehrdad Mahdavi , Chunhao Wang

For a $d$-dimensional log-concave distribution $\pi(\theta) \propto e^{-f(\theta)}$ constrained to a convex body $K$, the problem of outputting samples from a distribution $\nu$ which is $\varepsilon$-close in infinity-distance…

Data Structures and Algorithms · Computer Science 2022-11-14 Oren Mangoubi , Nisheeth K. Vishnoi

Sampling from a high-dimensional distribution is a fundamental task in statistics, engineering, and the sciences. A canonical approach is the Langevin Algorithm, i.e., the Markov chain for the discretized Langevin Diffusion. This is the…

Statistics Theory · Mathematics 2022-11-01 Jason M. Altschuler , Kunal Talwar

We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimization as presented in Raginsky et al. (2017). Non-asymptotic…

Statistics Theory · Mathematics 2021-02-03 Ngoc Huy Chau , Éric Moulines , Miklos Rásonyi , Sotirios Sabanis , Ying Zhang

A key task in Bayesian statistics is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). However, without any assumptions, sampling (even approximately) can be #P-hard, and few…

Machine Learning · Computer Science 2018-12-03 Rong Ge , Holden Lee , Andrej Risteski

We propose a computationally efficient random walk on a convex body which rapidly mixes and closely tracks a time-varying log-concave distribution. We develop general theoretical guarantees on the required number of steps; this number can…

Machine Learning · Statistics 2013-09-25 Hariharan Narayanan , Alexander Rakhlin

Langevin algorithms are gradient descent methods with additive noise. They have been used for decades in Markov chain Monte Carlo (MCMC) sampling, optimization, and learning. Their convergence properties for unconstrained non-convex…

Machine Learning · Computer Science 2020-12-23 Andrew Lamperski

A canonical algorithm for log-concave sampling is the Langevin Algorithm, aka the Langevin Diffusion run with some discretization stepsize $\eta > 0$. This discretization leads the Langevin Algorithm to have a stationary distribution…

Machine Learning · Statistics 2024-10-22 Jason M. Altschuler , Kunal Talwar

A key task in Bayesian machine learning is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). One prevalent example of this is sampling posteriors in parametric distributions,…

Machine Learning · Computer Science 2020-09-10 Rong Ge , Holden Lee , Andrej Risteski

Sampling from log-concave distributions is a well researched problem that has many applications in statistics and machine learning. We study the distributions of the form $p^{*}\propto\exp(-f(x))$, where…

Machine Learning · Computer Science 2019-09-13 Ruoqi Shen , Yin Tat Lee

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

Given a Lipschitz or smooth convex function $\, f:K \to \mathbb{R}$ for a bounded polytope $K \subseteq \mathbb{R}^d$ defined by $m$ inequalities, we consider the problem of sampling from the log-concave distribution $\pi(\theta) \propto…

Data Structures and Algorithms · Computer Science 2022-11-16 Oren Mangoubi , Nisheeth K. Vishnoi

Sampling from Gibbs distributions and computing their log-partition function are fundamental tasks in statistics, machine learning, and statistical physics. While efficient algorithms are known for log-concave densities, the worst-case…

Machine Learning · Statistics 2026-04-24 David Holzmüller , Francis Bach

We consider the problem of sampling from a log-concave distribution $\pi(\theta) \propto e^{-f(\theta)}$ constrained to a polytope $K:=\{\theta \in \mathbb{R}^d: A\theta \leq b\}$, where $A\in \mathbb{R}^{m\times d}$ and $b \in…

Data Structures and Algorithms · Computer Science 2024-09-09 Oren Mangoubi , Nisheeth K. Vishnoi

In large-data applications, such as the inference process of diffusion models, it is desirable to design sampling algorithms with a high degree of parallelization. In this work, we study the adaptive complexity of sampling, which is the…

Data Structures and Algorithms · Computer Science 2025-05-21 Huanjian Zhou , Baoxiang Wang , Masashi Sugiyama

Sampling from discrete distributions is a ubiquitous task in machine learning, recently revisited by the emergence of discrete diffusion models. While Langevin algorithms constitute the state of the art for continuous spaces, discrete…

Statistics Theory · Mathematics 2026-02-18 Armand Gissler , Saeed Saremi , Francis Bach

We present an optimization algorithm that can identify a global minimum of a potentially nonconvex smooth function with high probability, assuming the Gibbs measure of the potential satisfies a logarithmic Sobolev inequality. Our…

Optimization and Control · Mathematics 2025-09-16 Daniel Cortild , Claire Delplancke , Nadia Oudjane , Juan Peypouquet

We study online convex optimization in the random order model, recently proposed by \citet{garber2020online}, where the loss functions may be chosen by an adversary, but are then presented to the online algorithm in a uniformly random…

Machine Learning · Computer Science 2021-06-30 Uri Sherman , Tomer Koren , Yishay Mansour

We consider estimating the marginal likelihood in settings with independent and identically distributed (i.i.d.) data. We propose estimating the predictive distributions in a sequential factorization of the marginal likelihood in such…

Machine Learning · Statistics 2019-11-19 Scott A. Cameron , Hans C. Eggers , Steve Kroon

Sampling from a target distribution induced by training data is central to Bayesian learning, with Stochastic Gradient Langevin Dynamics (SGLD) serving as a key tool for scalable posterior sampling and decentralized variants enabling…

Optimization and Control · Mathematics 2025-11-18 Waheed U. Bajwa , Mert Gurbuzbalaban , Mustafa Ali Kutbay , Lingjiong Zhu , Muhammad Zulqarnain
‹ Prev 1 2 3 10 Next ›