Tutorial - Learn to Optimize

Ke Tang,Southern University of Science and Technology China; Shengcai Liu, Southern University of Science and Technology,China ABSTRACT: The huge success of machine learning, with AlphaGo, AlphaStar, and AlphaFold hailed as milestones, has boosted lots of enthusiasm in the Artificial Intelligence (AI) community on whether machine learning could achieve further breakthrough in other AI-related domains. Optimization problems might be among the first ones that came into mind, for their tight relationship with machine learning and wide applications in the real world. On the other hand, the concept of integrating learning and optimization has been a long-standing theme of research in many sub-areas of computational intelligence, under the name of algorithm selection, parameter tuning, automated algorithm configuration, hyper-heuristic, transfer optimization, etc. This tutorial will first review these relevant topics in a unified framework dubbed “Learn to Optimize” (LTO). We hope such a review would provide a big picture to the following questions which might be of interest to the whole AI community:1.So far, how good could a machine solve optimization problems by learning from past experience.2.How to apply LTO technology in practice (if they could be used)?Based on the review, latest research that falls in the scope of LTO, such as automatic construction approaches for parallel algorithm portfolios and reinforcement learning for neural solvers, will be introduced with more details.