English
Related papers

Related papers: Sampling from Log-Concave Distributions with Infin…

200 papers

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 study the mixing time of two popular discrete-time Markov chains in continuous space, the Unadjusted Langevin Algorithm and the Proximal Sampler, which are discretizations of the Langevin dynamics. We extend mixing time analyses for…

Statistics Theory · Mathematics 2025-02-13 Siddharth Mitra , Andre Wibisono

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

We study the Riemannian Langevin Algorithm for the problem of sampling from a distribution with density $\nu$ with respect to the natural measure on a manifold with metric $g$. We assume that the target density satisfies a log-Sobolev…

Machine Learning · Computer Science 2022-04-25 Khashayar Gatmiry , Santosh S. Vempala

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

We study differentially private (DP) algorithms for stochastic convex optimization: the problem of minimizing the population loss given i.i.d. samples from a distribution over convex loss functions. A recent work of Bassily et al. (2019)…

Machine Learning · Computer Science 2020-05-12 Vitaly Feldman , Tomer Koren , Kunal Talwar

We propose a method for estimating a log-concave density on $\mathbb R^d$ from samples, under the assumption that there exists an orthogonal transformation that makes the components of the random vector independent. While log-concave…

Statistics Theory · Mathematics 2024-12-20 Sharvaj Kubal , Christian Campbell , Elina Robeva

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 design a new, fast algorithm for agnostically learning univariate probability distributions whose densities are well approximated by piecewise polynomial functions. Let $f$ be the density function of an arbitrary univariate distribution,…

Data Structures and Algorithms · Computer Science 2015-06-03 Jayadev Acharya , Ilias Diakonikolas , Jerry Li , Ludwig Schmidt

The $L^k$-Wasserstein distance $\mathbb{W}_k (k\ge 1)$ and the probability distance $\mathbb{W}_\psi$ induced by a concave function $\psi$, are estimated between different diffusion processes with singular coefficients. As applications, the…

Probability · Mathematics 2023-11-07 Xing Huang , Panpan Ren , Feng-Yu Wang

Error bounds are derived for sampling and estimation using a discretization of an intrinsically defined Langevin diffusion with invariant measure $\text{d}\mu_\phi \propto e^{-\phi} \mathrm{dvol}_g $ on a compact Riemannian manifold. Two…

Statistics Theory · Mathematics 2025-12-10 Karthik Bharath , Alexander Lewis , Akash Sharma , Michael V Tretyakov

The estimation of information measures of continuous distributions based on samples is a fundamental problem in statistics and machine learning. In this paper, we analyze estimates of differential entropy in $K$-dimensional Euclidean space,…

Information Theory · Computer Science 2021-11-29 Georg Pichler , Pablo Piantanida , Günther Koliander

We propose a fast stochastic Hamilton Monte Carlo (HMC) method, for sampling from a smooth and strongly log-concave distribution. At the core of our proposed method is a variance reduction technique inspired by the recent advance in…

Machine Learning · Statistics 2020-10-20 Difan Zou , Pan Xu , Quanquan Gu

In this work, we propose a first-order sampling method called the Metropolis-adjusted Preconditioned Langevin Algorithm for approximate sampling from a target distribution whose support is a proper convex subset of $\mathbb{R}^{d}$. Our…

Computation · Statistics 2025-02-27 Vishwak Srinivasan , Andre Wibisono , Ashia Wilson

In this paper, we propose a novel class of Piecewise Deterministic Markov Processes (PDMPs) that are designed to sample from probability distributions $\pi$ supported on a convex set $\mathcal{M}$. This class of PDMPs adapts the concept of…

Computation · Statistics 2026-05-01 Joël Tatang Demano , Paul Dobson , Konstantinos Zygalakis

We introduce a theoretical framework for sampling from unnormalized densities based on a smoothing scheme that uses an isotropic Gaussian kernel with a single fixed noise scale. We prove one can decompose sampling from a density (minimal…

Machine Learning · Statistics 2023-10-02 Saeed Saremi , Ji Won Park , Francis Bach

Sampling logconcave functions arising in statistics and machine learning has been a subject of intensive study. Recent developments include analyses for Langevin dynamics and Hamiltonian Monte Carlo (HMC). While both approaches have…

Data Structures and Algorithms · Computer Science 2018-12-18 Yin Tat Lee , Zhao Song , Santosh S. Vempala

Let $X_1,\dots,X_n$ be i.i.d. log-concave random vectors in $\mathbb R^d$ with mean 0 and covariance matrix $\Sigma$. We study the problem of quantifying the normal approximation error for $W=n^{-1/2}\sum_{i=1}^nX_i$ with explicit…

Probability · Mathematics 2023-05-30 Xiao Fang , Yuta Koike

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

We consider the outstanding problem of sampling from an unnormalized density that may be non-log-concave and multimodal. To enhance the performance of simple Markov chain Monte Carlo (MCMC) methods, techniques of annealing type have been…

Machine Learning · Statistics 2025-02-18 Wei Guo , Molei Tao , Yongxin Chen
‹ Prev 1 3 4 5 6 7 10 Next ›