GradientLess Descent

From statwiki
Revision as of 17:24, 31 October 2020 by Jlavilez (talk | contribs)
Jump to navigation Jump to search
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

Introduction

Motivation and Set-up

A general optimisation question can be formulated by asking to minimise an objective function [math]\displaystyle{ f : \mathbb{R}^n \to \mathbb{R} }[/math], which means finding: \begin{align*} x^* = \mathrm{argmin}_{x \in \mathbb{R}^n} f(x) \end{align*}

Depending on the nature of [math]\displaystyle{ f }[/math], different settings may be considered:

  • Convex vs non-convex objective functions;
  • Differentiable vs non-differentiable objective functions;
  • Allowed function or gradient computations;
  • Noisy/Stochastic oracle access.

For the purpose of this paper, we consider convex smooth objective noiseless functions, where we have access to function computations but not gradient computations. This class of functions is quite common in practice; for instance, they make special appearances in the reinforcement learning literature.

Zeroth-Order Optimisation

GradientLess Descent Algorithm

Proof of correctness