English

Model-based Asynchronous Hyperparameter and Neural Architecture Search

Machine Learning 2020-07-01 v2 Machine Learning

Abstract

We introduce a model-based asynchronous multi-fidelity method for hyperparameter and neural architecture search that combines the strengths of asynchronous Hyperband and Gaussian process-based Bayesian optimization. At the heart of our method is a probabilistic model that can simultaneously reason across hyperparameters and resource levels, and supports decision-making in the presence of pending evaluations. We demonstrate the effectiveness of our method on a wide range of challenging benchmarks, for tabular data, image classification and language modelling, and report substantial speed-ups over current state-of-the-art methods. Our new methods, along with asynchronous baselines, are implemented in a distributed framework which will be open sourced along with this publication.

Keywords

Cite

@article{arxiv.2003.10865,
  title  = {Model-based Asynchronous Hyperparameter and Neural Architecture Search},
  author = {Aaron Klein and Louis C. Tiao and Thibaut Lienart and Cedric Archambeau and Matthias Seeger},
  journal= {arXiv preprint arXiv:2003.10865},
  year   = {2020}
}