arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2402.09598stat.MLcs.LGmath.STstat.COstat.TH
收藏

MCMC驱动的学习

MCMC-driven learning

Alexandre Bouchard-Côté, Trevor Campbell, Geoff Pleiss, Nikola Surjanovic

AI总结:

本文旨在将MCMC与机器学习交叉领域的多种问题统一在一个共同框架内,使各问题的理论和方法得以相互转化与推广。

摘要:

本文旨在作为《Markov Chain Monte Carlo手册》的一章。本章的目标是将Markov chain Monte Carlo (MCMC) 与机器学习交叉领域的各种问题统一在一个共同框架内,包括black-box variational inference、adaptive MCMC、normalizing flow construction与transport-assisted MCMC、surrogate-likelihood MCMC、面向大数据MCMC的coreset construction、Markov chain gradient descent、Markovian score climbing等。通过统一,为各问题开发的理论与方法可被转化与推广。

英文摘要:

This paper is intended to appear as a chapter for the Handbook of Markov Chain Monte Carlo. The goal of this chapter is to unify various problems at the intersection of Markov chain Monte Carlo (MCMC) and machine learning$\unicode{x2014}$which includes black-box variational inference, adaptive MCMC, normalizing flow construction and transport-assisted MCMC, surrogate-likelihood MCMC, coreset construction for MCMC with big data, Markov chain gradient descent, Markovian score climbing, and more$\unicode{x2014}$within one common framework. By doing so, the theory and methods developed for each may be translated and generalized.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑