Neural Optimizer Search with Reinforcement Learning

Irwan Bello,Barret Zoph,Vijay Vasudevan,Quoc V. Le

Published 2017 in International Conference on Machine Learning

ABSTRACT

We present an approach to automate the process of discovering optimization methods, with a focus on deep learning architectures. We train a Recurrent Neural Network controller to generate a string in a domain specific language that describes a mathematical update equation based on a list of primitive functions, such as the gradient, running average of the gradient, etc. The controller is trained with Reinforcement Learning to maximize the performance of a model after a few epochs. On CIFAR-10, our method discovers several update rules that are better than many commonly used optimizers, such as Adam, RMSProp, or SGD with and without Momentum on a ConvNet model. We introduce two new optimizers, named PowerSign and AddSign, which we show transfer well and improve training on a variety of different tasks and architectures, including ImageNet classification and Google's neural machine translation system.

PUBLICATION RECORD

  • Publication year

    2017

  • Venue

    International Conference on Machine Learning

  • Publication date

    2017-08-06

  • Fields of study

    Mathematics, Computer Science

  • Identifiers
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-49 of 49 references · Page 1 of 1

CITED BY

Showing 1-100 of 403 citing papers · Page 1 of 5