Learning to Optimize

06/06/2016
by   Ke Li, et al.
0

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, which we believe to be the first method that can automatically discover a better 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/01/2017

Learning to Optimize Neural Nets

Learning to Optimize is a recently proposed framework for learning optim...
research
12/12/2019

Provably Efficient Exploration in Policy Optimization

While policy-based reinforcement learning (RL) achieves tremendous succe...
research
09/23/2020

Parameters for the best convergence of an optimization algorithm On-The-Fly

What really sparked my interest was how certain parameters worked better...
research
01/25/2021

Computational Workflows for Designing Input Devices

Input devices, such as buttons and sliders, are the foundation of any in...
research
03/10/2020

Learning to be Global Optimizer

The advancement of artificial intelligence has cast a new light on the d...
research
06/30/2023

TD Convergence: An Optimization Perspective

We study the convergence behavior of the celebrated temporal-difference ...
research
03/18/2023

Granular-ball Optimization Algorithm

The existing intelligent optimization algorithms are designed based on t...

Please sign up or login with your details

Forgot password? Click here to reset