Learning to Optimize: A Primer and A Benchmark

03/23/2021
by   Tianlong Chen, et al.
61

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/17/2019

A Survey of Optimization Methods from a Machine Learning Perspective

Machine learning develops rapidly, which has made many theoretical break...
08/10/2012

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

Designing a fast and efficient optimization method with local optima avo...
06/22/2022

Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization

Molecular optimization is a fundamental goal in the chemical sciences an...
02/17/2022

Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization

Black-box model-based optimization (MBO) problems, where the goal is to ...
02/08/2022

Teaching Networks to Solve Optimization Problems

Leveraging machine learning to optimize the optimization process is an e...
04/16/2022

Analytical Benchmark Problems for Multifidelity Optimization Methods

The paper presents a collection of analytical benchmark problems specifi...
02/01/2022

Tutorial on amortized optimization for learning to optimize over continuous domains

Optimization is a ubiquitous modeling tool that is often deployed in set...