arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.11366stat.MLcs.LG
收藏

随机坐标欠阻尼朗之万蒙特卡罗

Random Coordinate Underdamped Langevin Monte Carlo

University of Wisconsin-Madison(威斯康星大学麦迪逊分校);Duke University(杜克大学)

Zhiyan Ding, Qin Li, Jianfeng Lu, Stephen J. Wright

摘要:

欠阻尼朗之万蒙特卡罗(ULMC)是一种流行的马尔可夫链蒙特卡罗抽样方法。它需要在每次迭代时计算对数密度的全梯度,如果问题的维数很高,则这是一个昂贵的操作。我们提出了一种称为随机坐标ULMC(RC-ULMC)的采样方法,该方法在每次迭代时选择一个要更新的坐标,而其他坐标不变。我们研究了RC-ULMC的计算复杂度,并与经典的ULMC强对数凹概率分布。我们表明,RC-ULMC总是比经典的ULMC便宜,具有显着的成本降低时,问题是高度偏斜和高维。我们的复杂性约束RC-ULMC也紧的维度依赖。

英文摘要:

The Underdamped Langevin Monte Carlo (ULMC) is a popular Markov chain Monte Carlo sampling method. It requires the computation of the full gradient of the log-density at each iteration, an expensive operation if the dimension of the problem is high. We propose a sampling method called Random Coordinate ULMC (RC-ULMC), which selects a single coordinate at each iteration to be updated and leaves the other coordinates untouched. We investigate the computational complexity of RC-ULMC and compare it with the classical ULMC for strongly log-concave probability distributions. We show that RC-ULMC is always cheaper than the classical ULMC, with a significant cost reduction when the problem is highly skewed and high dimensional. Our complexity bound for RC-ULMC is also tight in terms of dimension dependence.

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。

↑