Hyperparameter optimization with approximate gradient - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Hyperparameter optimization with approximate gradient


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.

Dates and versions

hal-01386410 , version 1 (24-10-2016)



Fabian Pedregosa. Hyperparameter optimization with approximate gradient. Proceedings of the 33rd International Conference on Machine Learning, Jun 2016, New York, United States. ⟨hal-01386410⟩
103 View
0 Download



Gmail Facebook X LinkedIn More