Johan Segers — accepted AI-conference papers

2024

Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates

Rémi Leluc, Aymeric Dieuleveut, François Portier, Johan Segers, Aigerim Zhuman

ICML 2024poster

The Sliced-Wasserstein (SW) distance between probability measures is defined as the average of the Wasserstein distances resulting for the associated one-dimensional projections. As a consequence, the SW distance can be written as an integral with respect to the uniform measure on the sphere and the…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗

2022

A Quadrature Rule combining Control Variates and Adaptive Importance Sampling

Rémi Leluc, François Portier, Johan Segers, Aigerim Zhuman

NeurIPS 2022accept

Driven by several successful applications such as in stochastic gradient descent or in Bayesian computation, control variates have become a major tool for Monte Carlo integration. However, standard methods do not allow the distribution of the particles to evolve during the algorithm, as is the case…

Cited by 6 Source ↗PDF ↗Scholar ↗