Learning to Learn for Global Optimization of Black Box Functions

We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad range of derivative-free black-box functions, including Gaussian process bandits, simple control objectives, global optimization benchmarks and hyper-parameter tuning tasks. Up to the training horizon, the learned optimizers learn to tradeoff exploration and exploitation, and compare favourably with heavily engineered Bayesian optimization packages for hyper-parameter tuning.