arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2506.08031math.OC
收藏

具有 Bregman 距离的 Banach 空间中的随机 Krasnosel'skii–Mann 迭代

Stochastic Krasnosel skii-Mann Iterations in Banach Spaces with Bregman Distances

Saeed Hashemi Sababe, Ehsan Lotfali Ghasab

AI总结:

本文将随机 Krasnosel'skii–Mann 算法推广到带 Bregman 距离的自反 Banach 空间,证明不动点几乎必然收敛并给出非渐近残差界,且通过强化学习与镜像下降实验验证理论。

摘要:

我们提出了随机 Krasnosel'skii–Mann(SKM)算法的一种推广,将其扩展到赋予 Bregman 距离的自反 Banach 空间。在对偶空间中的标准鞅差噪声假设以及距离生成函数的温和条件下,我们建立了到不动点的几乎必然收敛性,并推导出依赖于生成函数一致凸模的非渐近残差界。文中还讨论了向自适应 Bregman 几何和鲁棒噪声模型的扩展。关于熵正则化强化学习和镜像下降的数值实验阐明了这些理论发现。

英文摘要:

We propose a generalization of the stochastic Krasnoselskil-Mann $(SKM)$ algorithm to reflexive Banach spaces endowed with Bregman distances. Under standard martingale-difference noise assumptions in the dual space and mild conditions on the distance-generating function, we establish almost-sure convergence to a fixed point and derive non-asymptotic residual bounds that depend on the uniform convexity modulus of the generating function. Extensions to adaptive Bregman geometries and robust noise models are also discussed. Numerical experiments on entropy-regularized reinforcement learning and mirror-descent illustrate the theoretical findings.

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。

↑