.png){kind=icon}
返回
Adaptive System Optimization Using Random Directions Stochastic Approximation
.png){kind=icon}
OA
AI
DOI：10.1109/TAC.2016.2600643.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We present new algorithms for simulation optimization using random directions stochastic approximation (RDSA). These include first-order (gradient) as well as second-order (Newton) schemes. We incorporate both continuous-valued as well as discrete-valued perturbations into both types of algorithms. The former are chosen to be independent and identically distributed (i.i.d.) symmetric uniformly distributed random variables (r.v.), while the latter are i.i.d. asymmetric Bernoulli r.v.s. Our Newton algorithm, with a novel Hessian estimation scheme, requires N-dimensional perturbations and three loss measurements per iteration, whereas the simultaneous perturbation Newton search algorithm of [1] requires 2N-dimensional perturbations and four loss measurements per iteration. We prove the asymptotic unbiasedness of both gradient and Hessian estimates and asymptotic (strong) convergence for both first-order and second-order schemes. We also provide asymptotic normality results, which in particular establish that the asymmetric Bernoulli variant of Newton RDSA method is better than 2SPSA of [1]. Numerical experiments are used to validate the theoretical results.
Keyword:
Random directions stochastic approximation (RDSA)
simultaneous perturbation stochastic approximation (SPSA)
stochastic approximation
stochastic optimization
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。