Better call Surrogates: A hybrid Evolutionary Algorithm for Hyperparameter optimization
Neural and Evolutionary Computing
2020-12-14 v1 Artificial Intelligence
Abstract
In this paper, we propose a surrogate-assisted evolutionary algorithm (EA) for hyperparameter optimization of machine learning (ML) models. The proposed STEADE model initially estimates the objective function landscape using RadialBasis Function interpolation, and then transfers the knowledge to an EA technique called Differential Evolution that is used to evolve new solutions guided by a Bayesian optimization framework. We empirically evaluate our model on the hyperparameter optimization problems as a part of the black box optimization challenge at NeurIPS 2020 and demonstrate the improvement brought about by STEADE over the vanilla EA.
Cite
@article{arxiv.2012.06453,
title = {Better call Surrogates: A hybrid Evolutionary Algorithm for Hyperparameter optimization},
author = {Subhodip Biswas and Adam D Cobb and Andreea Sistrunk and Naren Ramakrishnan and Brian Jalaian},
journal= {arXiv preprint arXiv:2012.06453},
year = {2020}
}
Comments
Accepted at the black box optimization challenge at NeurIPS 2020