From the 1 of 7 linked papers with an AI index.
7 papers
Computing Barycentres of Measures for Generic Transport Costs
Eloi Tanguy, Julie Delon, Nathaël Gozlan
The paper proposes and analyzes a fixed‑point algorithm for computing barycentres of probability measures under general transport costs, providing convergence guarantees and numeri…
Sliced Transport Plans
Eloi Tanguy, Laetitia Chapel, Julie Delon
Since the introduction of the Sliced Wasserstein distance in the literature, its simplicity and efficiency have made it one of the most interesting surrogate for the Wasserstein di…
Robust Barycenters of Persistence Diagrams
Keanu Sisouk, Eloi Tanguy, Julie Delon +1
This short paper presents a general approach for computing robust Wasserstein barycenters of persistence diagrams. The classical method consists in computing assignment arithmetic…
Explicit Universal and Approximate-Universal Kernels on Compact Metric Spaces
Eloi Tanguy
Universal kernels, whose Reproducing Kernel Hilbert Space is dense in the space of continuous functions are of great practical and theoretical interest. In this paper, we introduce…
Differentiable Expectation-Maximisation and Applications to Gaussian Mixture Model Optimal Transport
Samuel Boïté, Eloi Tanguy, Julie Delon +2
The Expectation-Maximisation (EM) algorithm is a central tool in statistics and machine learning, widely used for latent-variable models such as Gaussian Mixture Models (GMMs). Des…
Properties of Discrete Sliced Wasserstein Losses
Eloi Tanguy, Rémi Flamary, Julie Delon
The Sliced Wasserstein (SW) distance has become a popular alternative to the Wasserstein distance for comparing probability measures. Widespread applications include image processi…