A Comparative Study of Hyperparameter Tuning Methods

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dasgupta, Subhasis, Sen, Jaydip
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914928838836224
author Dasgupta, Subhasis
Sen, Jaydip
author_facet Dasgupta, Subhasis
Sen, Jaydip
contents The study emphasizes the challenge of finding the optimal trade-off between bias and variance, especially as hyperparameter optimization increases in complexity. Through empirical analysis, three hyperparameter tuning algorithms Tree-structured Parzen Estimator (TPE), Genetic Search, and Random Search are evaluated across regression and classification tasks. The results show that nonlinear models, with properly tuned hyperparameters, significantly outperform linear models. Interestingly, Random Search excelled in regression tasks, while TPE was more effective for classification tasks. This suggests that there is no one-size-fits-all solution, as different algorithms perform better depending on the task and model type. The findings underscore the importance of selecting the appropriate tuning method and highlight the computational challenges involved in optimizing machine learning models, particularly as search spaces expand.
format Preprint
id arxiv_https___arxiv_org_abs_2408_16425
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Comparative Study of Hyperparameter Tuning Methods
Dasgupta, Subhasis
Sen, Jaydip
Machine Learning
The study emphasizes the challenge of finding the optimal trade-off between bias and variance, especially as hyperparameter optimization increases in complexity. Through empirical analysis, three hyperparameter tuning algorithms Tree-structured Parzen Estimator (TPE), Genetic Search, and Random Search are evaluated across regression and classification tasks. The results show that nonlinear models, with properly tuned hyperparameters, significantly outperform linear models. Interestingly, Random Search excelled in regression tasks, while TPE was more effective for classification tasks. This suggests that there is no one-size-fits-all solution, as different algorithms perform better depending on the task and model type. The findings underscore the importance of selecting the appropriate tuning method and highlight the computational challenges involved in optimizing machine learning models, particularly as search spaces expand.
title A Comparative Study of Hyperparameter Tuning Methods
topic Machine Learning
url https://arxiv.org/abs/2408.16425