Saved in:
Bibliographic Details
Main Author: Hai, Vu Tuan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.13545
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908272955490304
author Hai, Vu Tuan
author_facet Hai, Vu Tuan
contents Machine learning has been widely applied in many aspects, but training a machine learning model is increasingly difficult. There are more optimization problems named "black-box" where the relationship between model parameters and outcomes is uncertain or complex to trace. Currently, optimizing black-box models that need a large number of query observations and parameters becomes difficult. To overcome the drawbacks of the existing algorithms, in this study, we propose a zeroth-order method that originally came from quantum computing called the parameter-shift rule, which has used a lesser number of parameters than previous methods.
format Preprint
id arxiv_https___arxiv_org_abs_2503_13545
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimization on black-box function by parameter-shift rule
Hai, Vu Tuan
Machine Learning
Machine learning has been widely applied in many aspects, but training a machine learning model is increasingly difficult. There are more optimization problems named "black-box" where the relationship between model parameters and outcomes is uncertain or complex to trace. Currently, optimizing black-box models that need a large number of query observations and parameters becomes difficult. To overcome the drawbacks of the existing algorithms, in this study, we propose a zeroth-order method that originally came from quantum computing called the parameter-shift rule, which has used a lesser number of parameters than previous methods.
title Optimization on black-box function by parameter-shift rule
topic Machine Learning
url https://arxiv.org/abs/2503.13545