English

Gradient-based Hyperparameter Optimization through Reversible Learning

Machine Learning 2015-04-03 v3 Machine Learning

Abstract

Tuning hyperparameters of learning algorithms is hard because gradients are usually unavailable. We compute exact gradients of cross-validation performance with respect to all hyperparameters by chaining derivatives backwards through the entire training procedure. These gradients allow us to optimize thousands of hyperparameters, including step-size and momentum schedules, weight initialization distributions, richly parameterized regularization schemes, and neural network architectures. We compute hyperparameter gradients by exactly reversing the dynamics of stochastic gradient descent with momentum.

Keywords

Cite

@article{arxiv.1502.03492,
  title  = {Gradient-based Hyperparameter Optimization through Reversible Learning},
  author = {Dougal Maclaurin and David Duvenaud and Ryan P. Adams},
  journal= {arXiv preprint arXiv:1502.03492},
  year   = {2015}
}

Comments

10 figures. Submitted to ICML

R2 v1 2026-06-22T08:28:04.317Z