Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Learning to Optimize
Ke Li, Jitendra Malik
Nov 04, 2016 (modified: Mar 04, 2017)ICLR 2017 conference submissionreaders: everyone
Abstract:Algorithm design is a laborious process and often requires many iterations of ideation and validation. In this paper, we explore automating algorithm design and present a method to learn an optimization algorithm. We approach this problem from a reinforcement learning perspective and represent any particular optimization algorithm as a policy. We learn an optimization algorithm using guided policy search and demonstrate that the resulting algorithm outperforms existing hand-engineered algorithms in terms of convergence speed and/or the final objective value.
TL;DR:We explore learning an optimization algorithm automatically.
Keywords:Reinforcement Learning, Optimization
Enter your feedback below and we'll get back to you as soon as possible.