Théo Lacombe

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 18

Top Topics

Persistent Homology

Chinese Restaurant Process

Trained Neural Networks

Robust Estimation

Top Venues

Publications

Mathieu Carrière, Marc Theveneau, Théo Lacombe
Diffeomorphic interpolation for efficient persistence-based topological optimization. CoRR (2024)
Charles Arnal, Felix Hensel, Mathieu Carrière, Théo Lacombe, Hiroaki Kurihara, Yuichi Ike, Frédéric Chazal
MAGDiff: Covariate Data Set Shift Detection via Activation Graphs of Neural Networks. Trans. Mach. Learn. Res. 2024 (2024)
Jacob Leygonie, Mathieu Carrière, Théo Lacombe, Steve Oudot
A gradient sampling algorithm for stratified maps with applications to topological data analysis. Math. Program. 202 (1) (2023)
Felix Hensel, Charles Arnal, Mathieu Carrière, Théo Lacombe, Hiroaki Kurihara, Yuichi Ike, Frédéric Chazal
MAGDiff: Covariate Data Set Shift Detection via Activation Graphs of Deep Neural Networks. CoRR (2023)
Théo Lacombe
An Homogeneous Unbalanced Regularized Optimal Transport Model with Applications to Optimal Transport with Boundary. AISTATS (2023)
Yasuaki Hiraoka, Yusuke Imoto, Killian Meehan, Théo Lacombe, Toshiaki Yachimura
Topological Node2vec: Enhanced Graph Embedding via Persistent Homology. CoRR (2023)
Thibault de Surrel, Felix Hensel, Mathieu Carrière, Théo Lacombe, Yuichi Ike, Hiroaki Kurihara, Marc Glisse, Frédéric Chazal
RipsNet: a general architecture for fast and robust estimation of the persistent homology of point clouds. TAG-ML (2022)
Thibault de Surrel, Felix Hensel, Mathieu Carrière, Théo Lacombe, Yuichi Ike, Hiroaki Kurihara, Marc Glisse, Frédéric Chazal
RipsNet: a general architecture for fast and robust estimation of the persistent homology of point clouds. CoRR (2022)
Jacob Leygonie, Mathieu Carrière, Théo Lacombe, Steve Oudot
A Gradient Sampling Algorithm for Stratified Maps with Applications to Topological Data Analysis. CoRR (2021)
Théo Lacombe, Yuichi Ike, Mathieu Carrière, Frédéric Chazal, Marc Glisse, Yuhei Umeda
Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs. CoRR (2021)
Théo Lacombe, Yuichi Ike, Mathieu Carrière, Frédéric Chazal, Marc Glisse, Yuhei Umeda
Topological Uncertainty: Monitoring Trained Neural Networks through Persistence of Activation Graphs. IJCAI (2021)
Vincent Divol, Théo Lacombe
Understanding the topology and the geometry of the space of persistence diagrams via optimal partial transport. J. Appl. Comput. Topol. 5 (1) (2021)
Vincent Divol, Théo Lacombe
Estimation and Quantization of Expected Persistence Diagrams. ICML (2021)
Mathieu Carrière, Frédéric Chazal, Yuichi Ike, Théo Lacombe, Martin Royer, Yuhei Umeda
PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signatures. AISTATS (2020)
Mathieu Carrière, Frédéric Chazal, Yuichi Ike, Théo Lacombe, Martin Royer, Yuhei Umeda
A General Neural Network Architecture for Persistence Diagrams and Graph Classification. CoRR (2019)
Vincent Divol, Théo Lacombe
Understanding the Topology and the Geometry of the Persistence Diagram Space via Optimal Partial Transport. CoRR (2019)
Théo Lacombe, Marco Cuturi, Steve Oudot
Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport. CoRR (2018)
Théo Lacombe, Marco Cuturi, Steve Oudot
Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport. NeurIPS (2018)