Learning to Optimize: A Primer and A Benchmark

by   Tianlong Chen, et al.

Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods, aiming at reducing the laborious iterations of hand engineering. It automates the design of an optimization method based on its performance on a set of training problems. This data-driven procedure generates methods that can efficiently solve problems similar to those in the training. In sharp contrast, the typical and traditional designs of optimization methods are theory-driven, so they obtain performance guarantees over the classes of problems specified by the theory. The difference makes L2O suitable for repeatedly solving a certain type of optimization problems over a specific distribution of data, while it typically fails on out-of-distribution problems. The practicality of L2O depends on the type of target optimization, the chosen architecture of the method to learn, and the training procedure. This new paradigm has motivated a community of researchers to explore L2O and report their findings. This article is poised to be the first comprehensive survey and benchmark of L2O for continuous optimization. We set up taxonomies, categorize existing works and research directions, present insights, and identify open challenges. We also benchmarked many existing L2O approaches on a few but representative optimization problems. For reproducible research and fair benchmarking purposes, we released our software implementation and data in the package Open-L2O at https://github.com/VITA-Group/Open-L2O.


page 1

page 2

page 3

page 4


A Survey of Optimization Methods from a Machine Learning Perspective

Machine learning develops rapidly, which has made many theoretical break...

M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation

Learning to Optimize (L2O) has drawn increasing attention as it often re...

Curved Space Optimization: A Random Search based on General Relativity Theory

Designing a fast and efficient optimization method with local optima avo...

Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization

Molecular optimization is a fundamental goal in the chemical sciences an...

A new derivative-free optimization method: Gaussian Crunching Search

Optimization methods are essential in solving complex problems across va...

Teaching Networks to Solve Optimization Problems

Leveraging machine learning to optimize the optimization process is an e...

Improving the resolution of CryoEM single particle analysis

We present a new 3D refinement method for CryoEM single particle analysi...

Please sign up or login with your details

Forgot password? Click here to reset