中文
相关论文

相关论文: The query complexity of sampling from strongly log…

200 篇论文

We propose a new method called the Metropolis-adjusted Mirror Langevin algorithm for approximate sampling from distributions whose support is a compact and convex set. This algorithm adds an accept-reject filter to the Markov chain induced…

统计计算 · 统计学 2024-06-24 Vishwak Srinivasan , Andre Wibisono , Ashia Wilson

In this paper, we present near-optimal space bounds for Lp-samplers. Given a stream of updates (additions and subtraction) to the coordinates of an underlying vector x \in R^n, a perfect Lp sampler outputs the i-th coordinate with…

数据结构与算法 · 计算机科学 2010-12-23 Hossein Jowhari , Mert Sağlam , Gábor Tardos

In this paper, we revisit the recently established theoretical guarantees for the convergence of the Langevin Monte Carlo algorithm of sampling from a smooth and (strongly) log-concave density. We improve the existing results when the…

统计理论 · 数学 2017-07-31 Arnak S. Dalalyan

We present a framework that allows for the non-asymptotic study of the $2$-Wasserstein distance between the invariant distribution of an ergodic stochastic differential equation and the distribution of its numerical approximation in the…

机器学习 · 统计学 2021-09-27 J. M. Sanz-Serna , Konstantinos C. Zygalakis

In this paper, we provide tight lower bounds for the oracle complexity of minimizing high-order H\"older smooth and uniformly convex functions. Specifically, for a function whose $p^{th}$-order derivatives are H\"older continuous with…

最优化与控制 · 数学 2025-06-10 Cedar Site Bai , Brian Bullins

We investigate the weak-coupling limit, kappa going to infinity, of 3D simplicial gravity using Monte Carlo simulations and a Strong Coupling Expansion. With a suitable modification of the measure we observe a transition from a branched…

高能物理 - 格点 · 物理学 2015-06-25 P. Bialas , B. Petersson , G. Thorleifsson

The Underdamped Langevin Monte Carlo (ULMC) is a popular Markov chain Monte Carlo sampling method. It requires the computation of the full gradient of the log-density at each iteration, an expensive operation if the dimension of the problem…

机器学习 · 统计学 2020-10-23 Zhiyan Ding , Qin Li , Jianfeng Lu , Stephen J. Wright

We study a relaxation of the problem of coupling probability distributions -- a list of samples is generated from one distribution and an accept is declared if any one of these samples is identical to the sample generated from the other…

机器学习 · 计算机科学 2026-01-13 Joseph Rowan , Buu Phan , Ashish Khisti

We consider the problem of sampling from constrained distributions, which has posed significant challenges to both non-asymptotic analysis and algorithmic design. We propose a unified framework, which is inspired by the classical mirror…

机器学习 · 计算机科学 2021-01-01 Ya-Ping Hsieh , Ali Kavis , Paul Rolland , Volkan Cevher

We study the complexity of optimizing highly smooth convex functions. For a positive integer $p$, we want to find an $\epsilon$-approximate minimum of a convex function $f$, given oracle access to the function and its first $p$ derivatives,…

最优化与控制 · 数学 2021-12-06 Ankit Garg , Robin Kothari , Praneeth Netrapalli , Suhail Sherif

Hamiltonian Monte Carlo (HMC) is a Markov chain algorithm for sampling from a high-dimensional distribution with density $e^{-f(x)}$, given access to the gradient of $f$. A particular case of interest is that of a $d$-dimensional Gaussian…

机器学习 · 统计学 2022-09-27 Simon Apers , Sander Gribling , Dániel Szilágyi

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…

统计计算 · 统计学 2016-07-04 Thomas Bonis

We introduce a framework for proving lower bounds on computational problems over distributions against algorithms that can be implemented using access to a statistical query oracle. For such algorithms, access to the input distribution is…

计算复杂性 · 计算机科学 2016-08-16 Vitaly Feldman , Elena Grigorescu , Lev Reyzin , Santosh Vempala , Ying Xiao

In this paper we develop tools for studying limit theorems by means of convexity. We establish bounds for the discrepancy in total variation between probability measures $\mu$ and $\nu$ such that $\nu$ is log-concave with respect to $\mu$.…

概率论 · 数学 2022-10-24 Arturo Jaramillo , James Melbourne

We sharpen run-time analysis for algorithms under the partial rejection sampling framework. Our method yields improved bounds for: the cluster-popping algorithm for approximating all-terminal network reliability; the cycle-popping algorithm…

数据结构与算法 · 计算机科学 2018-12-14 Heng Guo , Kun He

This paper considers smooth strongly convex and strongly concave (SC-SC) stochastic saddle point (SSP) problems. Suppose there is an arbitrary oracle that in expectation returns an $\epsilon$-solution in the sense of certain gaps, which can…

最优化与控制 · 数学 2024-07-01 Dongyang Li , Haobin Li , Junyu Zhang

We study randomized algorithms for constrained optimization, in abstract frameworks that include, in strictly increasing generality: convex programming; LP-type problems; violator spaces; and a setting we introduce, consistent spaces. Such…

计算几何 · 计算机科学 2019-06-04 Kenneth L. Clarkson , Bernd Gärtner , Johannes Lengler , May Szedlak

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.…

In this work, we propose a new randomized algorithm for computing a low-rank approximation to a given matrix. Taking an approach different from existing literature, our method first involves a specific biased sampling, with an element being…

数据结构与算法 · 计算机科学 2014-10-16 Srinadh Bhojanapalli , Prateek Jain , Sujay Sanghavi

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…

概率论 · 数学 2018-12-27 Arnak S. Dalalyan , Lionel Riou-Durand