Skip to Main content Skip to Navigation
New interface
Conference papers

Algorithms for Hyper-Parameter Optimization

James Bergstra 1 R. Bardenet 2, 3 Yoshua Bengio 4 Balázs Kégl 2, 3, 5 
3 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : Several recent advances to the state of the art in image classification benchmarks have come from better configurations of existing techniques rather than novel ap- proaches to feature learning. Traditionally, hyper-parameter optimization has been the job of humans because they can be very efficient in regimes where only a few trials are possible. Presently, computer clusters and GPU processors make it pos- sible to run more trials and we show that algorithmic approaches can find better results. We present hyper-parameter optimization results on tasks of training neu- ral networks and deep belief networks (DBNs). We optimize hyper-parameters using random search and two new greedy sequential methods based on the ex- pected improvement criterion. Random search has been shown to be sufficiently efficient for learning neural networks for several datasets, but we show it is unreli- able for training DBNs. The sequential algorithms are applied to the most difficult DBN learning problems from [1] and find significantly better results than the best previously reported. This work contributes novel techniques for making response surface models P(y|x) in which many elements of hyper-parameter assignment (x) are known to be irrelevant given particular values of other elements.
Document type :
Conference papers
Complete list of metadata

Cited literature [22 references]  Display  Hide  Download
Contributor : Balázs Kégl Connect in order to contact the contributor
Submitted on : Sunday, November 20, 2011 - 10:39:52 PM
Last modification on : Friday, December 9, 2022 - 12:19:41 PM
Long-term archiving on: : Friday, November 16, 2012 - 11:31:30 AM


Files produced by the author(s)


  • HAL Id : hal-00642998, version 1


James Bergstra, R. Bardenet, Yoshua Bengio, Balázs Kégl. Algorithms for Hyper-Parameter Optimization. 25th Annual Conference on Neural Information Processing Systems (NIPS 2011), Dec 2011, Granada, Spain. ⟨hal-00642998⟩



Record views


Files downloads