Stochastic Hyperparameter Optimization through Hypernetworks
Jonathan Lorraine, David Duvenaud · arXiv (Cornell University) · 2018
Machine learning models are often tuned by nesting optimization of model weights inside the optimization of hyperparameters. We give a method to collapse this nested optimization into joint stochastic optimization of weights and hyperparameters. Our process trains a neural network to output approximately optimal weights as a function of hyperparameters. We show that our technique converges to locally optimal weights and hyperparameters for sufficiently large hypernetworks. We compare this method to standard hyperparameter optimization strategies and demonstrate its effectiveness for tuning thousands of hyperparameters.
Cited by 76 works. doi:10.48550/arxiv.1802.09419 Open-access PDF
Authors
References
- Gradient-based learning applied to document recognition
- Adam: A Method for Stochastic Optimization
- Practical Bayesian Optimization of Machine Learning Algorithms
- Random search for hyper-parameter optimization
- Approximation capabilities of multilayer feedforward networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- The Theory of Learning in Games
- Weight Uncertainty in Neural Networks
- Gradient-based Hyperparameter Optimization through Reversible Learning
- SMASH: One-Shot Model Architecture Search through HyperNetworks