English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Stochastic approximation (SA) is a key method used in statistical learning.Recently, its non-asymptotic convergence analysis has been considered in manypapers. However, most of the prior analyses are made under restrictiveassumptions such as unbiased gradient estimates and convex objective function,which significantly limit their applications to sophisticated tasks such asonline and reinforcement learning. These restrictions are all essentiallyrelaxed in this work. In particular, we analyze a general SA scheme to minimizea non-convex, smooth objective function. We consider update procedure whosedrift term depends on a state-dependent Markov chain and the mean field is notnecessarily of gradient type, covering approximate second-order method andallowing asymptotic bias for the one-step updates. We illustrate these settingswith the online EM algorithm and the policy-gradient method for average rewardmaximization in reinforcement learning.

Non-asymptotic Analysis of Biased Stochastic Approximation Scheme