@achakraborty

Neural Optimizer Search with Reinforcement Learning

, , , and . (2017)cite arxiv:1709.07417Comment: ICML 2017 Conference paper.

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.

Description

[1709.07417] Neural Optimizer Search with Reinforcement Learning

Links and resources

Tags

community

  • @achakraborty
  • @jk_itwm
  • @dblp
@achakraborty's tags highlighted