Workshop Program

The talk slides can be viewed by clicking the titles below. The workshop book is available here.

Monday, March 11

• 13:00--14:00 - Arrival & Registration

• 14:00--14:15 - Opening

• 14:15--15:00 - Alexander Mielke (Weierstraß-Institut, Berlin, Germany)

  • Hellinger--Kantorovich (a.k.a. Wasserstein-Fisher-Rao) Spaces and Gradient Flows

• 15:00--15:30 - Coffee Break

• 15:30--16:15 - Philippe Rigollet (Massachusetts Institute of Technology, Cambridge, USA)

  • The Emergence of Clusters in Self-attention Dynamics

• 16:15--17:00 - Olga Mula (Eindhoven University of Technology, Netherlands)

  • Reduced Models in Wasserstein Spaces for Forward and Inverse Problems

Tuesday, March 12

• 09:00--09:45 - Mark Peletier (Technical University of Eindhoven, Netherlands)

  • Singular-limit Analysis of Training with Noise Injection

• 09:45--10:30 - Bernhard Schmitzer (Georg-August-Universität Göttingen, Germany)

  • Entropic Transfer Operators for Data-driven Analysis of Dynamical Systems

• 10:30--11:00 - Coffee Break

• 11:00--11:45 - Julie Delon (Université Paris-Cité, France)

  • Optimal Transport with Invariances between Gaussian Mixture Models

• 11:45--12:30 - Virginie Ehrlacher (ENPC & INRIA, Paris, France)

  • Sparse Approximation of Multi-marginal Quantum Optimal Transport Problems with Moment Constraints: Application to Quantum Chemistry

• 12:30--14:00 - Lunch Break

• 14:00--14:45 - Daniel Kuhn (École Polytechnique Fédérale de Lausanne, Switzerland)

  • Distributionally Robust Linear Quadratic Control

• 14:45--15:30 - Hongseok Namkoong (Columbia University, New York, USA)

  • On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets

• 15:30--16:15 - Chaoyue Zhao (University of Washington, Seattle, USA)

  • Provably Convergent Policy Optimization via Metric-aware Trust Region Methods

• 18:00 - Conference Dinner at "Tapas Y Mas"

Wednesday, March 13

• 09:00--09:45 - Gabriel Peyré (CNRS & ENS, Paris, France)

  • Sparsistency for Inverse Optimal Transport

• 09:45--10:30 - Jan Maas (IST Austria, Klosterneuburg)

  • Anisotropy and the Infinitesimal Model

• 10:30--11:00 - Coffee Break

• 11:00--11:45 - Xue-Mei Li (École Polytechnique Fédérale de Lausanne, Switzerland)

  • Coarse Extrinsic Curvature

• 11:45--12:30 - Laetitia Chapel (Université de Bretagne-Sud & Institut Agro, France)

  • Fast Optimal Transport through Sliced Generalized Wasserstein Geodesics

• 12:30--14:00 - Lunch Break

• 14:00--14:45 - Massimiliano Pontil (IIT Genoa & UC London, Italy & UK)

  • Transfer Operator Learning

• 14:45--15:30 - Guillaume Carlier (Université Paris Dauphine - PSL, France)

  • Displacement Smoothness of Entropic Optimal Transport and Applications to some Evolution Equations and Systems

• 15:30-16:00 Poster Pitches

• 16:00-17:00 Poster Session & Coffee

Thursday, March 14

• 09:00--09:45 - Emtiyaz Khan (RIKEN, Tokyo, Japan)

  • The Bayesian Learning Rule

• 09:45--10:30 - Anna Korba (ENSAE & CREST, Palaiseau, France)

  • Sampling through Optimization of Discrepancies

• 10:30--11:00 - Coffee Break

• 11:00--11:45 - Jiaxin Shi (Google DeepMind, London, UK)

  • Stein’s Method for Modern Machine Learning: From Gradient Estimation to Generative Modeling

• 11:45--12:30 - Oliver Tse (Eindhoven University of Technology, Netherlands)

  • Variational Acceleration Methods in the Space of Probability Measures

• 12:30--14:30 - Lunch Break

• 14:30--15:15 - Claudia Totzeck (Bergische Universität Wuppertal, Germany)

  • Adjoint-based Optimal Control with Wasserstein-2 Metric

• 15:15--16:00 - Tim Laux (Universität Regensburg, Germany)

  • Emergence of Mean Curvature Flow in Learning

• 16:00-16:30 Poster Pitches

• 16:30-17:30 Poster Session & Coffee

Friday, March 15

• 09:00–09:45 - Taiji Suzuki (University of Tokyo, Japan)

  • Convergence of mean field Langevin dynamics and its application to neural network feature learning

• 09:45–10:30 - Wuchen Li (University of South Carolina, Columbia, USA)

  • Information Gamma Calculus: Convexity Analysis for Stochastic Differential Equations

• 10:30–11:00 - Coffee Break

• 11:00–11:45 - Mi Jung Park (Technical University of Denmark, Denmark)

  • Privacy-preserving Data Generation in the Era of Foundation Models: Generative Transfer Learning with Differential Privacy

• 11:45–12:30 - Discussion & Closing