TL;DR
This paper employs genetic programming to evolve novel continuous optimisers from scratch using a Turing-complete language, resulting in diverse strategies that often outperform traditional methods and generalize well across unseen problems.
Contribution
It introduces a method to automatically discover innovative continuous optimisers through evolution from scratch, demonstrating their diversity and generalization capabilities.
Findings
Evolved optimisers often outperform existing optimisers on unseen problems.
Evolved optimisers exhibit diverse and sometimes unusual optimization strategies.
Hybrid pools of optimisers enhance robustness across various problem types.
Abstract
This work uses genetic programming to explore the space of continuous optimisers, with the goal of discovering novel ways of doing optimisation. In order to keep the search space broad, the optimisers are evolved from scratch using Push, a Turing-complete, general-purpose, language. The resulting optimisers are found to be diverse, and explore their optimisation landscapes using a variety of interesting, and sometimes unusual, strategies. Significantly, when applied to problems that were not seen during training, many of the evolved optimisers generalise well, and often outperform existing optimisers. This supports the idea that novel and effective forms of optimisation can be discovered in an automated manner. This paper also shows that pools of evolved optimisers can be hybridised to further increase their generality, leading to optimisers that perform robustly over a broad variety of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
