194 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Laboratoire de Mathématiques d'OrsayFR12 papers
- Institut national de recherche en sciences et technologies du numériqueFR9 papers
- Centre Inria de SaclayFR7 papers
- Laboratoire de Probabilités, Statistique et ModélisationFR6 papers
- Centre National de la Recherche ScientifiqueFR4 papers
- Université Paris-SaclayFR4 papers
- Centre Inria d'Université Côte d'AzurFR3 papers
- École Polytechnique Fédérale de LausanneCH3 papers
- Institut de Mathématiques de ToulouseFR3 papers
- Institut National des Sciences Appliquées de ToulouseFR3 papers
- Université Toulouse III - Paul SabatierFR3 papers
- University of PotsdamDE3 papers
6 papers · 1 filter
Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs
Théo Lacombe, Yuichi Ike, Mathieu Carriere +3
Although neural networks are capable of reaching astonishing performances on a wide variety of contexts, properly training networks on complicated tasks requires expertise and can…
Generalized Penalty for Circular Coordinate Representation
Hengrui Luo, Alice Patania, Jisu Kim +1
Topological Data Analysis (TDA) provides novel approaches that allow us to analyze the geometrical shapes and topological structures of a dataset. As one important application, TDA…
Spectral Properties of Radial Kernels and Clustering in High Dimensions
David Cohen-Steiner, Alba Chiara de Vitis
In this paper, we study the spectrum and the eigenvectors of radial kernels for mixtures of distributions in . Our approach focuses on high dimensions and relies sole…
PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signatures
Mathieu Carrière, Frédéric Chazal, Yuichi Ike +3
Persistence diagrams, the most common descriptors of Topological Data Analysis, encode topological properties of data and have already proved pivotal in many different applications…
Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport
Théo Lacombe, Marco Cuturi, Steve Oudot
Persistence diagrams (PDs) are now routinely used to summarize the underlying topology of complex data. Despite several appealing properties, incorporating PDs in learning pipeline…
Domain Generalization by Marginal Transfer Learning
Gilles Blanchard, Aniket Anand Deshmukh, Urun Dogan +2
In the problem of domain generalization (DG), there are labeled training data sets from several related prediction problems, and the goal is to make accurate predictions on future…