Saved in:
Bibliographic Details
Main Author: Amin, Ahmad Ayaz
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.00208
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911820270272512
author Amin, Ahmad Ayaz
author_facet Amin, Ahmad Ayaz
contents Natural evolution strategies are a class of approximate-gradient black-box optimizers that have been successfully used for continuous parameter spaces. In this paper, we derive NES algorithms for discrete parameter spaces and demonstrate their effectiveness in tasks involving discrete parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00208
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Discrete Natural Evolution Strategies
Amin, Ahmad Ayaz
Neural and Evolutionary Computing
Optimization and Control
Natural evolution strategies are a class of approximate-gradient black-box optimizers that have been successfully used for continuous parameter spaces. In this paper, we derive NES algorithms for discrete parameter spaces and demonstrate their effectiveness in tasks involving discrete parameters.
title Discrete Natural Evolution Strategies
topic Neural and Evolutionary Computing
Optimization and Control
url https://arxiv.org/abs/2404.00208