中文
相关论文

相关论文: Convergence Analysis of Schr{\"o}dinger-F{\"o}llme…

200 篇论文

Sampling from probability distributions is an important problem in statistics and machine learning, specially in Bayesian inference when integration with respect to posterior distribution is intractable and sampling from the posterior is…

统计计算 · 统计学 2021-09-07 Jian Huang , Yuling Jiao , Lican Kang , Xu Liao , Jin Liu , Yanyan Liu

Generating samples from complex and high-dimensional distributions is ubiquitous in various scientific fields of statistical physics, Bayesian inference, scientific computing and machine learning. Very recently, Huang et al. (IEEE Trans.…

数值分析 · 数学 2026-01-01 Xiaojie Wang , Xiaoyan Zhang

Sampling is a fundamental algorithmic task in wide-ranging applications across multiple disciplines such as scientific computing, statistics and machine learning. In this paper, an efficient stochastic Runge-Kutta scheme is proposed to…

统计理论 · 数学 2026-05-27 Haotian Lin , Xiaojie Wang , Xiaoyan Zhang

Discrete time analogues of ergodic stochastic differential equations (SDEs) are one of the most popular and flexible tools for sampling high-dimensional probability measures. Non-asymptotic analysis in the $L^2$ Wasserstein distance of…

概率论 · 数学 2019-10-11 Mateusz B. Majka , Aleksandar Mijatović , Lukasz Szpruch

We provide new convergence guarantees in Wasserstein distance for diffusion-based generative models, covering both stochastic (DDPM-like) and deterministic (DDIM-like) sampling methods. We introduce a simple framework to analyze…

机器学习 · 计算机科学 2025-11-14 Eliot Beyler , Francis Bach

We study the problem of finding global minimizers of $V(x):\mathbb{R}^d\rightarrow\mathbb{R}$ approximately via sampling from a probability distribution $\mu_{\sigma}$ with density $p_{\sigma}(x)=\dfrac{\exp(-V(x)/\sigma)}{\int_{\mathbb…

最优化与控制 · 数学 2022-08-18 Yin Dai , Yuling Jiao , Lican Kang , Xiliang Lu , Jerry Zhijian Yang

We study the problem of unbiased estimation of expectations with respect to (w.r.t.) $\pi$ a given, general probability measure on $(\mathbb{R}^d,\mathcal{B}(\mathbb{R}^d))$ that is absolutely continuous with respect to a standard Gaussian…

统计计算 · 统计学 2022-10-26 Hamza Ruzayqat , Alexandros Beskos , Dan Crisan , Ajay Jasra , Nikolas Kantas

We consider the constrained sampling problem where the goal is to sample from a target distribution on a constrained domain. We propose skew-reflected non-reversible Langevin dynamics (SRNLD), a continuous-time stochastic differential…

机器学习 · 计算机科学 2025-04-16 Hengrong Du , Qi Feng , Changwei Tu , Xiaoyu Wang , Lingjiong Zhu

Although generative diffusion models (GDMs) are widely used in practice, their theoretical foundations remain limited, especially concerning the impact of different discretization schemes applied to the underlying stochastic differential…

数值分析 · 数学 2026-01-27 Emanuel Pfarr , Radu Timofte , Frank Werner

Score-based generative modeling with probability flow ordinary differential equations (ODEs) has achieved remarkable success in a variety of applications. While various fast ODE-based samplers have been proposed in the literature and…

机器学习 · 统计学 2025-08-12 Xuefeng Gao , Lingjiong Zhu

The smooth 1-Wasserstein distance (SWD) $W_1^\sigma$ was recently proposed as a means to mitigate the curse of dimensionality in empirical approximation while preserving the Wasserstein structure. Indeed, SWD exhibits parametric convergence…

统计理论 · 数学 2022-02-28 Ritwik Sadhu , Ziv Goldfeld , Kengo Kato

Score-based Generative Models (SGMs) approximate a data distribution by perturbing it with Gaussian noise and subsequently denoising it via a learned reverse diffusion process. These models excel at modeling complex data distributions and…

机器学习 · 计算机科学 2025-09-23 Stefano Bruno , Sotirios Sabanis

We introduce a novel unit-time ordinary differential equation (ODE) flow called the preconditioned F\"{o}llmer flow, which efficiently transforms a Gaussian measure into a desired target measure at time 1. To discretize the flow, we apply…

统计方法学 · 统计学 2023-11-08 Zhao Ding , Yuling Jiao , Xiliang Lu , Zhijian Yang , Cheng Yuan

We study the quantitative convergence of drift-diffusion PDEs that arise as Wasserstein gradient flows of linearly convex functions over the space of probability measures on ${\mathbb R}^d$. In this setting, the objective is in general not…

最优化与控制 · 数学 2025-07-17 Lénaïc Chizat , Maria Colombo , Xavier Fernández-Real

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, it seems to be a considerable restriction when the potentials are often required to be smooth (gradient Lipschitz). This paper…

统计计算 · 统计学 2022-02-23 Dao Nguyen

We present a novel inference approach that we call Sample Out-of-Sample (or SOS) inference. The approach can be used widely, ranging from semi-supervised learning to stress testing, and it is fundamental in the application of data-driven…

统计理论 · 数学 2021-03-22 Jose Blanchet , Yang Kang

Diffusion-based generative models have achieved remarkable performance across various domains, yet their practical deployment is often limited by high sampling costs. While prior work focuses on training objectives or individual solvers,…

机器学习 · 计算机科学 2026-02-16 Sangwoo Jo , Sungjoon Choi

We consider the optimization of a smooth and strongly convex objective using constant step-size stochastic gradient descent (SGD) and study its properties through the prism of Markov chains. We show that, for unbiased gradient estimates…

机器学习 · 统计学 2025-11-25 Ibrahim Merad , Stéphane Gaïffas

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

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…

统计理论 · 数学 2021-02-03 Ngoc Huy Chau , Éric Moulines , Miklos Rásonyi , Sotirios Sabanis , Ying Zhang
‹ 上一页 1 2 3 10 下一页 ›