AI-Driven Discovery in Combinatorics

Abstract: The last five years have seen AI-driven breakthroughs in research-level mathematics, sparking excitement and discussion about the future of the field. This talk will begin with an overview of these developments, from AI’s role in rigorously verifying proofs to its use in discovering mathematical constructions and formulating conjectures. AI for mathematics extends well beyond prompting GPT to prove a theorem; indeed, the field has seen many success stories from smaller, targeted models. The first half of the talk will survey the current landscape, and the second half will discuss recent work applying an LLM-based approach called evolutionary program synthesis to the challenge of finding combinatorial bijections.

machine learningcombinatorics

Audience: learners

Tropical mathematics and machine learning

Series comments: Tropical mathematics, machine learning, category theory and anything tech+math are welcome.