Automated Computational Energy Minimization of ML Algorithms using Constrained Bayesian Optimization

The paper presents a method that uses Constrained Bayesian Optimization (CBO) to minimize the energy consumption of machine learning models while ensuring their generalization performance stays above a specified threshold. By treating energy usage as the primary objective and performance as a constraint, the authors demonstrate that CBO can reduce training energy costs on both regression and classification tasks without sacrificing predictive accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.