Minimisation of Polyak-Łojasewicz Functions Using Random Zeroth-Order Oracles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Farzin, Amir Ali, Shames, Iman
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913775709323264
author Farzin, Amir Ali
Shames, Iman
author_facet Farzin, Amir Ali
Shames, Iman
contents The application of a zeroth-order scheme for minimising Polyak-Łojasewicz (PL) functions is considered. The framework is based on exploiting a random oracle to estimate the function gradient. The convergence of the algorithm to a global minimum in the unconstrained case and to a neighbourhood of the global minimum in the constrained case along with their corresponding complexity bounds are presented. The theoretical results are demonstrated via numerical examples.
format Preprint
id arxiv_https___arxiv_org_abs_2405_09106
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Minimisation of Polyak-Łojasewicz Functions Using Random Zeroth-Order Oracles
Farzin, Amir Ali
Shames, Iman
Optimization and Control
Machine Learning
The application of a zeroth-order scheme for minimising Polyak-Łojasewicz (PL) functions is considered. The framework is based on exploiting a random oracle to estimate the function gradient. The convergence of the algorithm to a global minimum in the unconstrained case and to a neighbourhood of the global minimum in the constrained case along with their corresponding complexity bounds are presented. The theoretical results are demonstrated via numerical examples.
title Minimisation of Polyak-Łojasewicz Functions Using Random Zeroth-Order Oracles
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2405.09106