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 2011.01868math.OCcs.LGcs.SYeess.SY
收藏

非线性双时间尺度随机逼近:收敛性和时间性能

Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance

Virginia Tech(弗吉尼亚理工大学)

Thinh T. Doan

摘要:

双时间尺度随机逼近是随机逼近的推广,在随机控制、优化和机器学习等领域有着广泛的应用。尽管它的流行,这种方法的理论保证,特别是其有限时间的性能,主要是实现了线性情况下,而非线性对应的结果是非常稀疏的。受经典奇异摄动系统控制理论的启发,本文研究了非线性双时间尺度随机逼近的渐近收敛性和有限时间分析.在一些相当标准的假设下,我们提供了一个公式,该公式表征了主迭代到所需解的收敛速度收敛速率。特别是,我们表明,该方法达到了预期的收敛率$\mathcal{O}(1/k^{2/3})$,其中$k$是迭代次数。在我们的分析中的关键思想是适当地选择两个步长来表征快速和慢速时间尺度迭代之间的耦合。

英文摘要:

Two-time-scale stochastic approximation, a generalized version of the popular stochastic approximation, has found broad applications in many areas including stochastic control, optimization, and machine learning. Despite its popularity, theoretical guarantees of this method, especially its finite-time performance, are mostly achieved for the linear case while the results for the nonlinear counterpart are very sparse. Motivated by the classic control theory for singularly perturbed systems, we study in this paper the asymptotic convergence and finite-time analysis of the nonlinear two-time-scale stochastic approximation. Under some fairly standard assumptions, we provide a formula that characterizes the rate of convergence of the main iterates to the desired solutions. In particular, we show that the method achieves a convergence in expectation at a rate $\mathcal{O}(1/k^{2/3})$, where $k$ is the number of iterations. The key idea in our analysis is to properly choose the two step sizes to characterize the coupling between the fast and slow-time-scale iterates.

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。

↑