# Neural Optimizer Search with Reinforcement Learning Source: [Neural Optimizer Search with Reinforcement Learning]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:46:17.527Z Authors: Irwan Bello, Barret Zoph, Vijay Vasudevan, Quoc V. Le Published: 2017-09-21T17:01:47.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImageNet 1k (test)](): Image Classification; ImageNet 1k (test); Top-1 Accuracy: 73.9. ## Original sources and implementation [Original paper]() [PDF]()