The Hi! PARIS AI Seminar Cycle is a monthly series showcasing leading research in Artificial Intelligence and Data Science. Held on the first Wednesday of each month, it brings together top scholars, students, and partners to explore AI’s scientific, business, and societal impact across key themes such as foundation models, trustworthy AI, and AI for science and engineering.
In this seminar, Bharath Sriperumbudur will talk about the Gromov-Wasserstein Distances: Entropic Regularization, Duality, and Sample Complexity.
In this seminar, Mikael Johansson will introduce an efficient algorithm for regularized optimal transport, a crucial technique in various domains.
Exceptional scientific seminar: “Towards general and flexible audio source separation and transcription”, by Jonathan Le Roux (MERL)
Exceptional scientific seminar: “Towards private and practical federated learning”, by Jan Ramon (MAGNET (Machine learniNG in large-scale information NETworks) group at Inria-Lille)
Exceptional scientific seminar: “Creating a New Paradigm for Research on Social Media”, by Chris Bail (Duke University and Director of the Duke Polarization Lab.)
Exceptional scientific seminar: “Pathfinder: Quasi-Newton Variational Inference”, by Bob Carpenter (Flatiron Institute, Center for Computational Mathematics)
Exceptional scientific seminar: “Recent advances in robust machine learning”, by Masashi Sugiyama (RIKEN-AIP / The University of Tokyo)
Proposed scientific seminar: “Conformal prediction beyond exchangeability”, by Aaditya Ramdas
Exceptional scientific seminar: “Non-Euclidean Differentially Private Stochastic Convex Optimization”, byCristobal Guzman
- 1
- 2