Resource-Aware Pareto-Optimal Automated Machine Learning Platform

Yao Yang, Andrew Nam, Mohamad M. Nasr-Azadani, Teresa Tung

Abstract

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.
BibTeX
@inproceedings{yang2020resource,
  author = {Yao Yang and Andrew Nam and Mohamad M. Nasr-Azadani and Teresa Tung},
  title = {{Resource-Aware Pareto-Optimal Automated Machine Learning Platform}},
  booktitle = {2020},
  year = {2020},
  doi = {10.1109/isriti51436.2020.9315336},
}
Figure