Théo Lacombe

According to our database, Théo Lacombe authored at least 15 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of three.

2024

MAGDiff: Covariate Data Set Shift Detection via Activation Graphs of Neural Networks.

Charles Arnal, Felix Hensel, Mathieu Carrière, Théo Lacombe, Hiroaki Kurihara, Yuichi Ike, Frédéric Chazal

Trans. Mach. Learn. Res., 2024

Topological Node2vec: Enhanced Graph Embedding via Persistent Homology.

Yasuaki Hiraoka, Yusuke Imoto, Théo Lacombe, Killian Meehan, Toshiaki Yachimura

J. Mach. Learn. Res., 2024

Diffeomorphic interpolation for efficient persistence-based topological optimization.

Mathieu Carrière, Marc Theveneau, Théo Lacombe

CoRR, 2024

2023

A gradient sampling algorithm for stratified maps with applications to topological data analysis.

Jacob Leygonie, Mathieu Carrière, Théo Lacombe, Steve Oudot

Math. Program., November, 2023

MAGDiff: Covariate Data Set Shift Detection via Activation Graphs of Deep Neural Networks.

Felix Hensel, Charles Arnal, Mathieu Carrière, Théo Lacombe, Hiroaki Kurihara, Yuichi Ike, Frédéric Chazal

CoRR, 2023

An Homogeneous Unbalanced Regularized Optimal Transport Model with Applications to Optimal Transport with Boundary.

Théo Lacombe

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

RipsNet: a general architecture for fast and robust estimation of the persistent homology of point clouds.

Thibault de Surrel, Felix Hensel, Mathieu Carrière, Théo Lacombe, Yuichi Ike, Hiroaki Kurihara, Marc Glisse, Frédéric Chazal

Proceedings of the Topological, 2022

2021

Understanding the topology and the geometry of the space of persistence diagrams via optimal partial transport.

Vincent Divol, Théo Lacombe

J. Appl. Comput. Topol., 2021

Topological Uncertainty: Monitoring Trained Neural Networks through Persistence of Activation Graphs.

Théo Lacombe, Yuichi Ike, Mathieu Carrière, Frédéric Chazal, Marc Glisse, Yuhei Umeda

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

Estimation and Quantization of Expected Persistence Diagrams.

Vincent Divol, Théo Lacombe

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Statistics for Topological Descriptors using optimal transport. (Statistiques sur les descripteurs topologiques à base de transport optimal).

Théo Lacombe

PhD thesis, 2020

PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signatures.

Mathieu Carrière, Frédéric Chazal, Yuichi Ike, Théo Lacombe, Martin Royer, Yuhei Umeda

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

A General Neural Network Architecture for Persistence Diagrams and Graph Classification.

Mathieu Carrière, Frédéric Chazal, Yuichi Ike, Théo Lacombe, Martin Royer, Yuhei Umeda

CoRR, 2019

Understanding the Topology and the Geometry of the Persistence Diagram Space via Optimal Partial Transport.

Vincent Divol, Théo Lacombe

CoRR, 2019

2018

Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport.

Théo Lacombe, Marco Cuturi, Steve Oudot

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018