Neural Optimizer Search using Reinforcement Learning

2017-08-01 · ICML 2017 8 · Irwan Bello, Barret Zoph, Vijay Vasudevan, Quoc V. Le

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translation reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Translation

Methods 이 논문이 사용한 방법론

Adam 설명 없음

RMSProp RMSProp is an unpublished adaptive learning rate optimizer proposed by Geoff Hinton. The motivation…

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

MolOpt: Autonomous Molecular Geometry Optimization using Multi-Agent Reinforcement Learning

2023-08-24 · ChemRxiv 2023 8 · Rohit Modee, Sarvesh Mehta, Siddhartha Laghuvarapu, U. Deva Priyakumar

In this paper, we propose MolOpt, the first attempt of its kind to use Multi-Agent Reinforcement Learning (MARL) for autonomous molecular geometry optimization (MGO). Typically MGO algorithms are hand-designed, but MolOp…

3D geometry Computational chemistry Molecular geometry optimization Multi-agent Reinforcement Learning+5

Learning to Optimize for Reinforcement Learning

2023-02-03 · Qingfeng Lan, A. Rupam Mahmood, Shuicheng Yan, Zhongwen Xu

In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-designed optimizers. Reinforcement learni…

Inductive Bias Meta-Learning reinforcement-learning Reinforcement Learning+1

Neural Optimizer Search with Reinforcement Learning

2017-09-21 · Irwan Bello, Barret Zoph, Vijay Vasudevan, Quoc V. Le

Machine Translation reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

In Defense of the Unitary Scalarization for Deep Multi-Task Learning

2022-01-11 · Vitaly Kurin, Alessandro De Palma, Ilya Kostrikov, Shimon Whiteson 외

Recent multi-task learning research argues against unitary scalarization, where training simply minimizes the sum of the task losses. Several ad-hoc multi-task optimization algorithms have instead been proposed, inspired…

Multi-Task Learning Reinforcement Learning (RL)

AIOptimizer - Software performance optimisation prototype for cost minimisation

2023-07-15 · Noopur Zambare

This study presents AIOptimizer, a prototype for a cost-reduction-based software performance optimisation tool. The study focuses on the design elements of AIOptimizer, including user-friendliness, scalability, accuracy,…

Fault Diagnosis Recommendation Systems reinforcement-learning