Learning to Optimize

Ke Li, Jitendra Malik

TL;DR: We explore learning an optimization algorithm automatically.

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.

Keywords: Reinforcement Learning, Optimization

Conflicts: eecs.berkeley.edu