Gradient-based Hyperparameter Optimization through Reversible Learning
Dougal Maclaurin, David Duvenaud, Ryan Prescott Adams · arXiv (Cornell University) · 2015
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.
Cited by 374 works. doi:10.48550/arxiv.1502.03492 Open-access PDF
Authors
References
- Long Short-Term Memory
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- On the importance of initialization and momentum in deep learning
- Practical Bayesian Optimization of Machine Learning Algorithms
- On the difficulty of training Recurrent Neural Networks
- Information theory, inference, and learning algorithms
- Theano: new features and speed improvements
- Why Does Unsupervised Pre-training Help Deep Learning?
- Choosing Multiple Parameters for Support Vector Machines