arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1507.02564math.PRcs.DScs.LG
收藏

对数凹分布抽样的投影朗之万蒙特卡罗方法

Sampling from a log-concave distribution with Projected Langevin Monte Carlo

Microsoft Research(微软研究院);Weizmann Institute(魏茨曼科学研究所);Université Paris-Dauphine(巴黎第九大学)

Sébastien Bubeck, Ronen Eldan, Joseph Lehec

摘要:

我们通过一个投影步骤,类似于投影随机梯度下降(SGD)的朗之万蒙特卡罗(LMC)算法,以compensate支持的措施。我们表明(投影)LMC允许在多项式时间内从具有光滑势的对数凹分布中进行采样。这给出了一个新的马尔可夫链从对数凹分布中采样。我们的主要结果表明,特别是当目标分布是均匀的,LMC混合在$\tilde{O}(n^7)$步骤(其中$n$是尺寸)。我们还提供了初步的实验证据表明,LMC执行至少以及打了就跑,其中一个更好的混合时间的$\tilde{O}(n^4)$由洛夫{á}sz和Vempala证明。

英文摘要:

We extend the Langevin Monte Carlo (LMC) algorithm to compactly supported measures via a projection step, akin to projected Stochastic Gradient Descent (SGD). We show that (projected) LMC allows to sample in polynomial time from a log-concave distribution with smooth potential. This gives a new Markov chain to sample from a log-concave distribution. Our main result shows in particular that when the target distribution is uniform, LMC mixes in $\tilde{O}(n^7)$ steps (where $n$ is the dimension). We also provide preliminary experimental evidence that LMC performs at least as well as hit-and-run, for which a better mixing time of $\tilde{O}(n^4)$ was proved by Lov{á}sz and Vempala.

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。

↑