Passer à la navigation principale Passer à la recherche Passer au contenu principal

Optimizing persistent homology based functions

  • Mathieu Carrière
  • , Frédéric Chazal
  • , Marc Glisse
  • , Yuichi Ike
  • , Hariprasad Kannan
  • , Yuhei Umeda
  • Université Côte D’Azur
  • Laboratoire de Mathématiques d'Orsay
  • National Institute for Environmental Studies

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

49 Citations (Scopus)

Résumé

Solving optimization tasks based on functions and losses with a topological flavor is a very active, growing field of research in data science and Topological Data Analysis, with applications in non-convex optimization, statistics and machine learning. However, the approaches proposed in the literature are usually anchored to a specific application and/or topological construction, and do not come with theoretical guarantees. To address this issue, we study the differentiability of a general map associated with the most common topological construction, that is, the persistence map. Building on real analytic geometry arguments, we propose a general framework that allows us to define and compute gradients for persistence-based functions in a very simple way. We also provide a simple, explicit and sufficient condition for convergence of stochastic subgradient methods for such functions. This result encompasses all the constructions and applications of topological optimization in the literature. Finally, we provide associated code, that is easy to handle and to mix with other non-topological methods and constraints, as well as some experiments showcasing the versatility of our approach.

langue originaleAnglais
titreProceedings of the 38th International Conference on Machine Learning, ICML 2021
EditeurML Research Press
Pages1294-1303
Nombre de pages10
ISBN (Electronique)9781713845065
étatPublié - 1 janv. 2021
Modification externeOui
Evénement38th International Conference on Machine Learning, ICML 2021 - Virtual, Online
Durée: 18 juil. 202124 juil. 2021

Série de publications

NomProceedings of Machine Learning Research
Volume139
ISSN (Electronique)2640-3498

Une conférence

Une conférence38th International Conference on Machine Learning, ICML 2021
La villeVirtual, Online
période18/07/2124/07/21

Empreinte digitale

Examiner les sujets de recherche de « Optimizing persistent homology based functions ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation