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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We consider a step search method for continuous optimization under astochastic setting where the function values and gradients are available onlythrough inexact probabilistic zeroth- and first-order oracles. Unlike thestochastic gradient method and its many variants, the algorithm does not use apre-specified sequence of step sizes but increases or decreases the step sizeadaptively according to the estimated progress of the algorithm. These oraclescapture multiple standard settings including expected loss minimization andzeroth-order optimization. Moreover, our framework is very general and allowsthe function and gradient estimates to be biased. The proposed algorithm issimple to describe and easy to implement. Under fairly general conditions onthe oracles, we derive a high probability tail bound on the iterationcomplexity of the algorithm when it is applied to non-convex, convex, andstrongly convex (more generally, those satisfying the PL condition) functions.Our analysis strengthens and extends prior results for stochastic step and linesearch methods.

High Probability Complexity Bounds for Adaptive Step Search Based on Stochastic Oracles