Searching for ribbons with machine learning

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Sergei Gukov, James Halverson, Ciprian Manolescu, Fabian Ruehle
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:Machine Learning: Science and Technology
Subjects:
Online Access:https://doi.org/10.1088/2632-2153/ade362
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849688048656187392
author Sergei Gukov
James Halverson
Ciprian Manolescu
Fabian Ruehle
author_facet Sergei Gukov
James Halverson
Ciprian Manolescu
Fabian Ruehle
author_sort Sergei Gukov
collection DOAJ
description 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.
format Article
id doaj-art-e42d8b44641f434fb39b82eda4d27ce9
institution DOAJ
issn 2632-2153
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series Machine Learning: Science and Technology
spelling doaj-art-e42d8b44641f434fb39b82eda4d27ce92025-08-20T03:22:09ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016202506510.1088/2632-2153/ade362Searching for ribbons with machine learningSergei Gukov0James Halverson1https://orcid.org/0000-0003-0535-2622Ciprian Manolescu2https://orcid.org/0000-0003-0600-8751Fabian Ruehle3https://orcid.org/0000-0002-8409-9823Dublin Institute for Advanced Studies , 10 Burlington Rd, Dublin, Ireland; California Institute of Technology , Pasadena, CA 91125, United States of AmericaDepartment of Physics, Northeastern University , 360 Huntington Avenue, Boston, MA 02115, United States of America; The NSF AI Institute for Artificial Intelligence and Fundamental Interactions , Boston, MA, United States of AmericaDepartment of Mathematics, Stanford University , 450 Jane Stanford Way, Building 380, Stanford, CA 94305-2125, United States of AmericaThe NSF AI Institute for Artificial Intelligence and Fundamental Interactions , Boston, MA, United States of America; Department of Physics and Department Mathematics, Northeastern University , 360 Huntington Avenue, Boston, MA 02115, United States of AmericaWe 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.https://doi.org/10.1088/2632-2153/ade362reinforcement learningBayesian optimizationknot theorylow-dimensional topology
spellingShingle Sergei Gukov
James Halverson
Ciprian Manolescu
Fabian Ruehle
Searching for ribbons with machine learning
Machine Learning: Science and Technology
reinforcement learning
Bayesian optimization
knot theory
low-dimensional topology
title Searching for ribbons with machine learning
title_full Searching for ribbons with machine learning
title_fullStr Searching for ribbons with machine learning
title_full_unstemmed Searching for ribbons with machine learning
title_short Searching for ribbons with machine learning
title_sort searching for ribbons with machine learning
topic reinforcement learning
Bayesian optimization
knot theory
low-dimensional topology
url https://doi.org/10.1088/2632-2153/ade362
work_keys_str_mv AT sergeigukov searchingforribbonswithmachinelearning
AT jameshalverson searchingforribbonswithmachinelearning
AT ciprianmanolescu searchingforribbonswithmachinelearning
AT fabianruehle searchingforribbonswithmachinelearning