AISTATS 2016poster92 citations

Unbounded Bayesian Optimization via Regularization

Bobak Shahriari, Alexandre Bouchard-Cote, Nando Freitas

Abstract

Bayesian optimization has recently emerged as a powerful and flexible tool in machine learning for hyperparameter tuning and more generally for the efficient global optimization of expensive black box functions. The established practice requires a user-defined bounded domain, which is assumed to contain the global optimizer. However, when little is known about the probed objective function, it can be difficult to prescribe such a domain. In this work, we modify the standard Bayesian optimization framework in a principled way to allow for unconstrained exploration of the search space. We introduce a new alternative method and compare it to a volume doubling baseline on two common synthetic benchmarking test functions. Finally, we apply our proposed methods on the task of tuning the stochastic gradient descent optimizer for both a multi-layered perceptron and a convolutional neural network on the MNIST dataset.

BibTeX
@InProceedings{pmlr-v51-shahriari16,
  title = 	 {Unbounded Bayesian Optimization via Regularization},
  author = 	 {Shahriari, Bobak and Bouchard-Cote, Alexandre and Freitas, Nando},
  booktitle = 	 {Proceedings of the 19th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {1168--1176},
  year = 	 {2016},
  editor = 	 {Gretton, Arthur and Robert, Christian C.},
  volume = 	 {51},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Cadiz, Spain},
  month = 	 {09--11 May},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v51/shahriari16.pdf},
  url = 	 {https://proceedings.mlr.press/v51/shahriari16.html},
  abstract = 	 {Bayesian optimization has recently emerged as a powerful and flexible tool in machine learning for hyperparameter tuning and more generally for the efficient global optimization of expensive black box functions. The established practice requires a user-defined bounded domain, which is assumed to contain the global optimizer. However, when little is known about the probed objective function, it can be difficult to prescribe such a domain. In this work, we modify the standard Bayesian optimization framework in a principled way to allow for unconstrained exploration of the search space. We introduce a new alternative method and compare it to a volume doubling baseline on two common synthetic benchmarking test functions. Finally, we apply our proposed methods on the task of tuning the stochastic gradient descent optimizer for both a multi-layered perceptron and a convolutional neural network on the MNIST dataset.}
}
Unbounded Bayesian Optimization via Regularization · AISTATS 2016