English

Learning to Learn without Gradient Descent by Gradient Descent

Machine Learning 2017-06-13 v6 Machine Learning

Abstract

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 trade-off exploration and exploitation, and compare favourably with heavily engineered Bayesian optimization packages for hyper-parameter tuning.

Keywords

Cite

@article{arxiv.1611.03824,
  title  = {Learning to Learn without Gradient Descent by Gradient Descent},
  author = {Yutian Chen and Matthew W. Hoffman and Sergio Gomez Colmenarejo and Misha Denil and Timothy P. Lillicrap and Matt Botvinick and Nando de Freitas},
  journal= {arXiv preprint arXiv:1611.03824},
  year   = {2017}
}

Comments

Accepted by ICML 2017. Previous version "Learning to Learn for Global Optimization of Black Box Functions" was published in the Deep Reinforcement Learning Workshop, NIPS 2016

R2 v1 2026-06-22T16:49:45.746Z