Searching for ribbons with machine learning
Open Access
- 18 June 2025
- journal article
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 6 (2) , 025065
Abstract
We apply Bayesian optimization and reinforcement learning to a problem in topology: the question of when a knot bounds a ribbon disk. This question is relevant in an approach to disproving the four-dimensional smooth Poincaré conjecture; using our programs, we rule out many potential counterexamples to the conjecture. We also show that the programs are successful in detecting many ribbon knots in the range of up to 70 crossings.Keywords
All Related Versions
Funding Information
- Simons Foundation (New Structures in Low- Dimensional Topology)
- Division of Physics (PHY-1848089)
- Division of Mathematical Sciences (DMS-1664227)
This publication has 17 references indexed in Scilit:
- Advancing mathematics by guiding human intuition with AINature, 2021
- Learning to unknotMachine Learning: Science and Technology, 2021
- Machine learning and algebraic approaches towards complete matter spectra in 4d F-theoryJournal of High Energy Physics, 2021
- Data science applications to string theoryPhysics Reports, 2020
- Machine Learning Line Bundle CohomologyFortschritte der Physik, 2019
- Branes with brains: exploring string vacua with deep reinforcement learningJournal of High Energy Physics, 2019
- The Search for Nonsymmetric Ribbon KnotsExperimental Mathematics, 2019
- Machine learning in the string landscapeJournal of High Energy Physics, 2017
- Khovanov homology and the slice genusInventiones Mathematicae, 2010
- Metabelian representations, twisted Alexander polynomials, knot slicing, and mutationMathematische Zeitschrift, 2009