Thibaut Le Gouic

About Me

Hi, I have been a Maitre de Conférence (Associate Professor) at the Institut de Mathématiques de Marseille and the Ecole Centrale de Marseille since 2014. I was on research sabbatical at the Faculty of Computer Science at HSE in 2018-2019 and at the Mathematics Department at the MIT in 2019-2021.

Research Interest

My general interests lie at the interaction of statistics, probability and geometry. More recently, I have been focusing my work on barycenters, sampling and optimal transport.

Find me online

Publications

  1. Le Gouic, Thibaut. “Recovering Metric from Full Ordinal Information.” Discrete & Computational Geometry (to appear)
  2. Le Gouic, Thibaut, Quentin Paris, Philippe Rigollet, and Austin J. Stromme. 2019. “Fast Convergence of Empirical Barycenters in Alexandrov Spaces and the Wasserstein Space.” Journal of the European Mathematical Society, 2022. - talk
  3. Perchet Vianney, Philippe Rigollet and Thibaut Le Gouic. 2022. “An algorithmic solution to the Blotto game using multi-marginal couplings.” Proceedings of the 23rd ACM Conference on Economics and Computation, 208-209
  4. Chewi, Sinho, Patrik Gerber, Chen Lu, Thibaut Le Gouic, and Philippe Rigollet. (2021). “The query complexity of sampling from strongly log-concave distributions in one dimension.” Conference on Learning Theory, 2041-2059
  5. Chewi, Sinho, Patrik Gerber, Chen Lu, Thibaut Le Gouic, and Philippe Rigollet (2021). “Rejection sampling from shape-constrained distributions in sublinear time.” International Conference on Artificial Intelligence and Statistics, 2249-2265
  6. Chewi, Sinho, Chen Lu, Kwangjun Ahn, Xiang Cheng, Thibaut Le Gouic, and Philippe Rigollet. 2021. “Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithm.” COLT 2021. - talk
  7. Chewi, Sinho, Julien Clancy, Thibaut Le Gouic, Philippe Rigollet, George Stepaniants, and Austin J. Stromme. 2020. “Fast and Smooth Interpolation on Wasserstein Space.” AISTATS 2021.
  8. Chewi, Sinho, Thibaut Le Gouic, Chen Lu, Tyler Maunu, and Philippe Rigollet. 2020. “SVGD as a Kernelized Wasserstein Gradient Flow of the Chi-Squared Divergence.” NeurIPS 2020.
  9. Chewi, Sinho, Thibaut Le Gouic, Chen Lu, Tyler Maunu, Philippe Rigollet, and Austin J. Stromme. 2020. “Exponential Ergodicity of Mirror-Langevin Diffusions.” NeurIPS 2020.
  10. Le Gouic, Thibaut. 2020. “A Note on Flatness of Non Separable Tangent Cone at a Barycenter.” Comptes Rendus. Mathématique 358(4):489–495.
  11. Ahidar-Coutrix, Adil, Thibaut Le Gouic, and Quentin Paris. 2019. “Convergence Rates for Empirical Barycenters in Metric Spaces: Curvature, Convexity and Extendable Geodesics.” Probability Theory and Related Fields 1–46. - talk
  12. Arias-Castro, Ery, and Thibaut Le Gouic. 2019. “Unconstrained and Curvature-Constrained Shortest-Path Distances and Their Approximation.” Discrete & Computational Geometry 62(1):1–28.
  13. Boissard, Emmanuel, Thibaut Le Gouic, and Jean-Michel Loubes. 2015. “Distribution’s Template Estimate with Wasserstein Metrics.” Bernoulli 21(2):740–759.
  14. Le Gouic, Thibaut, and Quentin Paris. 2018. “A Notion of Stability for K-Means Clustering.” Electronic Journal of Statistics 12(2):4239–4263.
  15. Le Gouic, Thibaut, and Jean-Michel Loubes. 2017. “Existence and Consistency of Wasserstein Barycenters.” Probability Theory and Related Fields 168(3–4):901–917. - talk
  16. Boissard, Emmanuel, and Thibaut Le Gouic. 2014. “On the Mean Speed of Convergence of Empirical and Occupation Measures in Wasserstein Distance.” Pp. 539–563 in Annales de l’IHP Probabilités et statistiques. Vol. 50.

Preprints

  1. Daaloul, Chiheb, Thibaut Le Gouic, Jacques Liandrat, and Magali Tournus. 2021 “Sampling From the Wasserstein Barycenter.” ArXiv:2105.01706 - talk
  2. Le Gouic, Thibaut, Jean-Michel Loubes, and Philippe Rigollet. 2020 “Projection to Fairness in Statistical Learning.” ArXiv:2005.11720
  3. Le Gouic, Thibaut. 2015. “Mass Localization.” ArXiv:1506.04136.