使用正则化瓦塞尔斯坦近似值的无噪声采样算法的收敛性

Fuqun Han, Stanley Osher, Wuchen Li
{"title":"使用正则化瓦塞尔斯坦近似值的无噪声采样算法的收敛性","authors":"Fuqun Han, Stanley Osher, Wuchen Li","doi":"arxiv-2409.01567","DOIUrl":null,"url":null,"abstract":"In this work, we investigate the convergence properties of the backward\nregularized Wasserstein proximal (BRWP) method for sampling a target\ndistribution. The BRWP approach can be shown as a semi-implicit time\ndiscretization for a probability flow ODE with the score function whose density\nsatisfies the Fokker-Planck equation of the overdamped Langevin dynamics.\nSpecifically, the evolution of the score function is computed using a kernel\nformula derived from the regularized Wasserstein proximal operator. By applying\nthe Laplace method to obtain the asymptotic expansion of this kernel formula,\nwe establish guaranteed convergence in terms of the Kullback-Leibler divergence\nfor the BRWP method towards a strongly log-concave target distribution. Our\nanalysis also identifies the optimal and maximum step sizes for convergence.\nFurthermore, we demonstrate that the deterministic and semi-implicit BRWP\nscheme outperforms many classical Langevin Monte Carlo methods, such as the\nUnadjusted Langevin Algorithm (ULA), by offering faster convergence and reduced\nbias. Numerical experiments further validate the convergence analysis of the\nBRWP method.","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"12 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Convergence of Noise-Free Sampling Algorithms with Regularized Wasserstein Proximals\",\"authors\":\"Fuqun Han, Stanley Osher, Wuchen Li\",\"doi\":\"arxiv-2409.01567\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this work, we investigate the convergence properties of the backward\\nregularized Wasserstein proximal (BRWP) method for sampling a target\\ndistribution. The BRWP approach can be shown as a semi-implicit time\\ndiscretization for a probability flow ODE with the score function whose density\\nsatisfies the Fokker-Planck equation of the overdamped Langevin dynamics.\\nSpecifically, the evolution of the score function is computed using a kernel\\nformula derived from the regularized Wasserstein proximal operator. By applying\\nthe Laplace method to obtain the asymptotic expansion of this kernel formula,\\nwe establish guaranteed convergence in terms of the Kullback-Leibler divergence\\nfor the BRWP method towards a strongly log-concave target distribution. Our\\nanalysis also identifies the optimal and maximum step sizes for convergence.\\nFurthermore, we demonstrate that the deterministic and semi-implicit BRWP\\nscheme outperforms many classical Langevin Monte Carlo methods, such as the\\nUnadjusted Langevin Algorithm (ULA), by offering faster convergence and reduced\\nbias. Numerical experiments further validate the convergence analysis of the\\nBRWP method.\",\"PeriodicalId\":501379,\"journal\":{\"name\":\"arXiv - STAT - Statistics Theory\",\"volume\":\"12 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - STAT - Statistics Theory\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.01567\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - STAT - Statistics Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.01567","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

在这项工作中,我们研究了用于目标分布采样的后向规则化瓦瑟斯坦近似(BRWP)方法的收敛特性。BRWP 方法可视为概率流 ODE 的半隐式时间离散化,其得分函数的密度满足过阻 Langevin 动力学的 Fokker-Planck 方程。通过应用拉普拉斯方法获得该核公式的渐近展开,我们确定了 BRWP 方法在 Kullback-Leibler 分歧方面对强对数凹目标分布的保证收敛性。我们的分析还确定了收敛的最佳步长和最大步长。此外,我们还证明了确定性和半隐式 BRWP 方案优于许多经典的朗格文蒙特卡罗方法,如调整朗格文算法(ULA),收敛速度更快,偏差更小。数值实验进一步验证了 BRWP 方法的收敛性分析。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Convergence of Noise-Free Sampling Algorithms with Regularized Wasserstein Proximals
In this work, we investigate the convergence properties of the backward regularized Wasserstein proximal (BRWP) method for sampling a target distribution. The BRWP approach can be shown as a semi-implicit time discretization for a probability flow ODE with the score function whose density satisfies the Fokker-Planck equation of the overdamped Langevin dynamics. Specifically, the evolution of the score function is computed using a kernel formula derived from the regularized Wasserstein proximal operator. By applying the Laplace method to obtain the asymptotic expansion of this kernel formula, we establish guaranteed convergence in terms of the Kullback-Leibler divergence for the BRWP method towards a strongly log-concave target distribution. Our analysis also identifies the optimal and maximum step sizes for convergence. Furthermore, we demonstrate that the deterministic and semi-implicit BRWP scheme outperforms many classical Langevin Monte Carlo methods, such as the Unadjusted Langevin Algorithm (ULA), by offering faster convergence and reduced bias. Numerical experiments further validate the convergence analysis of the BRWP method.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信