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 2011.05423math.PR
收藏

某些并行蒙特卡罗方法的低温极限分析和optimization

Analysis and optimization of certain parallel Monte Carlo methods in the low temperature limit

Paul Dupuis, Guo-Jhen Wu

摘要:

亚稳性是马尔可夫链蒙特卡罗方法面临的一个严峻挑战。在本文中,我们提出了算法设计,以满足这一挑战的方法。我们考虑的设计问题是无限交换方案的温度选择,这是广泛使用的并行回火方案的限制时,交换率趋于无穷大。我们使用一个最近开发的工具的经验措施的小噪声扩散的分析转换成一个明确的最优化问题的方差减少问题。我们对最优化问题的第一个分析是在双井模型的设置中,并且它表明除了可能的最高温度之外,温度比的最佳选择是等比数列。在相同的设置中,我们确定了两个不同的来源的方差减少,并显示它们的竞争如何确定最佳的最高温度。在一般的多井设置,我们证明了一个纯粹的等比数列的温度比总是接近最佳的,与性能差距,几何衰减的温度的数量。

英文摘要:

Metastability is a formidable challenge to Markov chain Monte Carlo methods. In this paper we present methods for algorithm design to meet this challenge. The design problem we consider is temperature selection for the infinite swapping scheme, which is the limit of the widely used parallel tempering scheme obtained when the swap rate tends to infinity. We use a recently developed tool for the analysis of the empirical measure of a small noise diffusion to transform the variance reduction problem into an explicit optimization problem. Our first analysis of the optimization problem is in the setting of a double well model, and it shows that the optimal selection of temperature ratios is a geometric sequence except possibly the highest temperature. In the same setting we identify two different sources of variance reduction, and show how their competition determines the optimal highest temperature. In the general multi-well setting we prove that a pure geometric sequence of temperature ratios is always nearly optimal, with a performance gap that decays geometrically in the number of temperatures.

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。

↑