Machine Learning

Neural Optimizer Search with Reinforcement Learning

This topic contains 0 replies, has 1 voice, and was last updated by  arXiv 1 year, 2 months ago.

  • arXiv
    5 pts

    Neural Optimizer Search with Reinforcement Learning

    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.

    Neural Optimizer Search with Reinforcement Learning
    by Irwan Bello, Barret Zoph, Vijay Vasudevan, Quoc V. Le

You must be logged in to reply to this topic.