On Zeroth-Order Stochastic Convex Optimization via Random Walks

Liang, Tengyuan, Narayanan, Hariharan, Rakhlin, Alexander

arXiv.org Machine Learning 

We propose a method for zeroth order stochastic convex optimization that attains the suboptimality rate of $\tilde{\mathcal{O}}(n^{7}T^{-1/2})$ after $T$ queries for a convex bounded function $f:{\mathbb R}^n\to{\mathbb R}$. The method is based on a random walk (the \emph{Ball Walk}) on the epigraph of the function. The randomized approach circumvents the problem of gradient estimation, and appears to be less sensitive to noisy function evaluations compared to noiseless zeroth order methods.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found