arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.00629stat.MLcs.LGmath.OC
收藏

有偏随机逼近格式的非渐近性分析

Non-asymptotic Analysis of Biased Stochastic Approximation Scheme

École Polytechnique(巴黎综合理工学院);University of Warsaw(华沙大学);The Chinese University of Hong Kong(香港中文大学)

Belhal Karimi, Blazej Miasojedow, Eric Moulines, Hoi-To Wai

摘要:

随机逼近(SA)是统计学习中的一种重要方法。近年来,关于它的非渐近收敛性的分析已在许多文献中得到了研究。然而,大多数先验分析都是在无偏梯度估计和凸目标函数等限制性假设下进行的,这大大限制了它们在在线和强化学习等复杂任务中的应用。这些限制在这项工作中基本上都得到了放松。特别是,我们分析了一个一般的SA计划,以尽量减少非凸,光滑的目标函数。我们考虑了漂移项依赖于状态依赖马尔可夫链且平均场不一定是梯度型的更新过程,覆盖了近似二阶方法,并允许一步更新的渐近偏差.我们用在线期望最大化算法和强化学习中平均奖励最大化的策略梯度方法来说明这些设置。

英文摘要:

Stochastic approximation (SA) is a key method used in statistical learning. Recently, its non-asymptotic convergence analysis has been considered in many papers. However, most of the prior analyses are made under restrictive assumptions such as unbiased gradient estimates and convex objective function, which significantly limit their applications to sophisticated tasks such as online and reinforcement learning. These restrictions are all essentially relaxed in this work. In particular, we analyze a general SA scheme to minimize a non-convex, smooth objective function. We consider update procedure whose drift term depends on a state-dependent Markov chain and the mean field is not necessarily of gradient type, covering approximate second-order method and allowing asymptotic bias for the one-step updates. We illustrate these settings with the online EM algorithm and the policy-gradient method for average reward maximization in reinforcement learning.

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。

↑