In this study, we introduce a novel platform Resource-Aware AutoML (RA-AutoML) which enables flexible and generalized algorithms to build machine learning models subjected to multiple objectives, as well as resource and hard-ware constraints. RA-AutoML intelligently conducts Hyper-Parameter Search(HPS) as well as Neural Architecture Search (NAS) to build models optimizing predefined objectives. RA-AutoML is a versatile framework that allows user to prescribe many resource/hardware constraints along with objectives demanded by the problem at hand or business requirements. At its core, RA-AutoML relies on our in-house search-engine algorithm,MOBOGA, which combines a modified constraint-aware Bayesian Optimization and Genetic Algorithm to construct Pareto optimal candidates. Our experiments on CIFAR-10 dataset shows very good accuracy compared to results obtained by state-of-art neural network models, while subjected to resource constraints in the form of model size.
@article{arxiv.2011.00073,
title = {Resource-Aware Pareto-Optimal Automated Machine Learning Platform},
author = {Yao Yang and Andrew Nam and Mohamad M. Nasr-Azadani and Teresa Tung},
journal= {arXiv preprint arXiv:2011.00073},
year = {2020}
}
Comments
Accepted for International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), IEEE. December 2020