English

Continuation Path Learning for Homotopy Optimization

Machine Learning 2023-07-25 v1 Artificial Intelligence Neural and Evolutionary Computing

Abstract

Homotopy optimization is a traditional method to deal with a complicated optimization problem by solving a sequence of easy-to-hard surrogate subproblems. However, this method can be very sensitive to the continuation schedule design and might lead to a suboptimal solution to the original problem. In addition, the intermediate solutions, often ignored by classic homotopy optimization, could be useful for many real-world applications. In this work, we propose a novel model-based approach to learn the whole continuation path for homotopy optimization, which contains infinite intermediate solutions for any surrogate subproblems. Rather than the classic unidirectional easy-to-hard optimization, our method can simultaneously optimize the original problem and all surrogate subproblems in a collaborative manner. The proposed model also supports real-time generation of any intermediate solution, which could be desirable for many applications. Experimental studies on different problems show that our proposed method can significantly improve the performance of homotopy optimization and provide extra helpful information to support better decision-making.

Keywords

Cite

@article{arxiv.2307.12551,
  title  = {Continuation Path Learning for Homotopy Optimization},
  author = {Xi Lin and Zhiyuan Yang and Xiaoyuan Zhang and Qingfu Zhang},
  journal= {arXiv preprint arXiv:2307.12551},
  year   = {2023}
}

Comments

Accepted by the 40th International Conference on Machine Learning (ICML 2023)