中文
相关论文

相关论文: Non-asymptotic convergence bounds for modified tam…

200 篇论文

In this article, we consider the problem of sampling from a probability measure $\pi$ having a density on $\mathbb{R}^d$ known up to a normalizing constant, $x\mapsto \mathrm{e}^{-U(x)} / \int_{\mathbb{R}^d} \mathrm{e}^{-U(y)} \mathrm{d}…

统计方法学 · 统计学 2018-11-27 Nicolas Brosse , Alain Durmus , Éric Moulines , Sotirios Sabanis

In this article we propose a novel taming Langevin-based scheme called $\mathbf{sTULA}$ to sample from distributions with superlinearly growing log-gradient which also satisfy a Log-Sobolev inequality. We derive non-asymptotic convergence…

概率论 · 数学 2023-11-16 Iosif Lytras , Sotirios Sabanis

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, the canonical Euler Maruyama discretization of the Langevin diffusion process, referred as Unadjusted Langevin Algorithm (ULA),…

统计计算 · 统计学 2021-07-28 Dao Nguyen , Xin Dang , Yixin Chen

In this paper, we study the numerical discretization of stochastic differential equations with locally Lipschitz, super-linearly growing drift, and the resulting implications for sampling from non-log-concave distributions satisfying a…

概率论 · 数学 2026-05-26 Iosif Lytras , Angelos Ntousis

Standard first-order Langevin algorithms such as the unadjusted Langevin algorithm (ULA) are obtained by discretizing the Langevin diffusion and are widely used for sampling in machine learning because they scale to high dimensions and…

机器学习 · 统计学 2025-09-25 Mert Gurbuzbalaban , Hoang M. Nguyen , Xicheng Zhang , Lingjiong Zhu

We consider non-convex stochastic optimization problems where the objective functions have super-linearly growing and discontinuous stochastic gradients. In such a setting, we provide a non-asymptotic analysis for the tamed unadjusted…

最优化与控制 · 数学 2023-05-03 Dong-Young Lim , Ariel Neufeld , Sotirios Sabanis , Ying Zhang

A well-known first-order method for sampling from log-concave probability distributions is the Unadjusted Langevin Algorithm (ULA). This work proposes a new annealing step-size schedule for ULA, which allows to prove new convergence…

统计理论 · 数学 2020-07-03 Paul Rolland , Armin Eftekhari , Ali Kavis , Volkan Cevher

Motivated by applications in deep learning, where the global Lipschitz continuity condition is often not satisfied, we examine the problem of sampling from distributions with super-linearly growing log-gradients. We propose a novel tamed…

统计理论 · 数学 2025-06-06 Iosif Lytras , Sotirios Sabanis , Ying Zhang

In this paper, we propose two new algorithms, namely, aHOLA and aHOLLA, to sample from high-dimensional target distributions with possibly super-linearly growing potentials. We establish non-asymptotic convergence bounds for aHOLA in…

统计理论 · 数学 2025-08-11 Ariel Neufeld , Ying Zhang

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…

机器学习 · 统计学 2024-05-29 Iosif Lytras , Panayotis Mertikopoulos

Artificial neural networks (ANNs) are typically highly nonlinear systems which are finely tuned via the optimization of their associated, non-convex loss functions. In many cases, the gradient of any such loss function has superlinear…

机器学习 · 计算机科学 2023-01-18 Attila Lovas , Iosif Lytras , Miklós Rásonyi , Sotirios Sabanis

Langevin dynamics are widely used in sampling high-dimensional, non-Gaussian distributions whose densities are known up to a normalizing constant. In particular, there is strong interest in unadjusted Langevin algorithms (ULA), which…

统计方法学 · 统计学 2024-10-24 Benjamin J. Zhang , Youssef M. Marzouk , Konstantinos Spiliopoulos

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…

统计计算 · 统计学 2018-03-30 Alain Durmus , Szymon Majewski , Błażej Miasojedow

In this article, we study the problem of sampling from distributions whose densities are not necessarily smooth nor logconcave. We propose a simple Langevin-based algorithm that does not rely on popular but computationally challenging…

机器学习 · 统计学 2025-12-02 Tim Johnston , Iosif Lytras , Nikolaos Makras , Sotirios Sabanis

We consider the problem of sampling distributions stemming from non-convex potentials with Unadjusted Langevin Algorithm (ULA). We prove the stability of the discrete-time ULA to drift approximations under the assumption that the potential…

机器学习 · 统计学 2025-09-01 Marien Renaud , Valentin De Bortoli , Arthur Leclaire , Nicolas Papadakis

We consider in this paper the problem of sampling a high-dimensional probability distribution $\pi$ having a density with respect to the Lebesgue measure on $\mathbb{R}^d$, known up to a normalization constant $x \mapsto \pi(x)=…

统计理论 · 数学 2018-07-17 Alain Durmus , Eric Moulines

In this paper, we study a method to sample from a target distribution $\pi$ over $\mathbb{R}^d$ having a positive density with respect to the Lebesgue measure, known up to a normalisation factor. This method is based on the Euler…

统计理论 · 数学 2016-12-20 Alain Durmus , Eric Moulines

In this paper, we focus on non-asymptotic bounds related to the Euler scheme of an ergodic diffusion with a possibly multiplicative diffusion term (non-constant diffusion coefficient). More precisely, the objective of this paper is to…

概率论 · 数学 2022-09-23 Gilles Pages , Fabien Panloup

The Metropolis-adjusted Langevin algorithm (MALA) is a Metropolis-Hastings method for approximate sampling from continuous distributions. We derive upper bounds for the contraction rate in Kantorovich-Rubinstein-Wasserstein distance of the…

概率论 · 数学 2014-01-17 Andreas Eberle

We introduce adaptive, tuning-free step size schedules for gradient-based sampling algorithms obtained as time-discretizations of Wasserstein gradient flows. The result is a suite of tuning-free sampling algorithms, including tuning-free…

统计方法学 · 统计学 2025-10-30 Louis Sharrock , Christopher Nemeth
‹ 上一页 1 2 3 10 下一页 ›