Hyperparameter optimization with approximate gradient
Pedregosa, Fabian (2016), Hyperparameter optimization with approximate gradient, Proceedings of the 33rd International Conference on Machine Learning, volume 48, Proceedings of Machine Learning Research, p. 15
TypeCommunication / Conférence
External document linkhttp://proceedings.mlr.press/v48/
Conference titleInternational Conference on Machine Learning
Conference cityNew York
Conference countryUnited States
Book titleProceedings of the 33rd International Conference on Machine Learning, volume 48
MetadataShow full item record
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Abstract (EN)Most models in machine learning contain at least one hyperparameter to control for model complexity. Choosing an appropriate set of hyperparameters is both crucial in terms of model accuracy and computationally challenging. In this work we propose an algorithm for the optimization of continuous hyperparameters using inexact gradient information. An advantage of this method is that hyperparameters can be updated before model parameters have fully converged. We also give sufficient conditions for the global convergence of this method, based on regularity conditions of the involved functions and summability of errors. Finally, we validate the empirical performance of this method on the estimation of regularization constants of L2-regularized logistic regression and kernel Ridge regression. Empirical benchmarks indicate that our approach is highly competitive with respect to state of the art methods.
Subjects / KeywordsHyperparameter optimization; gradient
Showing items related by title and author.