Skip to yearly menu bar Skip to main content


Poster

Neural Optimizer Search using Reinforcement Learning

Irwan Bello · Barret Zoph · Vijay Vasudevan · Quoc Le

Gallery #134

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 specific domain 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. These optimizers can also be transferred to perform well on different neural network architectures, including Google’s neural machine translation system.

Live content is unavailable. Log in and register to view live content