Lénaïc Chizat

CNRS researcher at Laboratoire de Mathématiques d'Orsay
photo de lenaic 

I am a CNRS researcher at LMO, the math department of Université Paris-Sud. In 2018, I was a post-doc researcher at INRIA Paris working with Francis Bach. In 2017, I have completed a PhD in applied mathematics at Université Paris-Dauphine (CEREMADE) and École Normale Supérieure (DMA) working with G. Peyré and F-X. Vialard. My research interests include:

  • optimal transport and variational problems in the space of measures

  • continuous optimization algorithms (convex and non-convex)

  • applications to machine learning and signal processing

my email 



  • L. Chizat, F. Bach. A Note on Lazy Training in Differentiable Programming. Technical report HAL-01945578, 2018. [pdf]

  • A. Genevay, L. Chizat, F. Bach, M. Cuturi, G. Peyré. Sample Complexity of Sinkhorn divergences. Technical report, arXiv-1810.02733, 2018. [pdf]

  • L. Chizat, F. Bach. On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport. Advances in Neural Information Processing Systems (NeurIPS), 2018. [pdf] [poster]

  • L. Chizat, G. Peyré, B. Schmitzer, F-X. Vialard, Unbalanced Optimal Transport: Dynamic and Kantorovich formulations. Journal of Functional Analysis, 2018. [article] [pdf]

  • L. Chizat, G. Peyré, B. Schmitzer, F-X. Vialard, Scaling Algorithms for Unbalanced Optimal Transport Problems. Mathematics of Computation, 2018. [pdf]


  • A. Thibault, L. Chizat, C. Dossal, N. Papadakis, Overrelaxed Sinkhorn-Knopp Algorithm for Regularized Optimal Transport. Technical report, arXiv-1711.01851, presented at the NIPS 2017 Workshop on Optimal Transport & Machine Learning. [pdf]

  • L. Chizat Unbalanced Optimal Transport: Models, Numerical Methods, Applications. PhD thesis, PSL Research University, 2017. [pdf]

  • L. Chizat, S. Di Marino, A tumor growth model of Hele-Shaw type as a gradient flow. Technical report, arXiv-1712.06124, 2017. [pdf]

  • G. Peyré, L. Chizat , F-X. Vialard, J. Solomon, Quantum Optimal Transport for Tensor Field Processing. European Journal of Applied Mathematics, 2017. [pdf]


  • L. Chizat, G. Peyré, B. Schmitzer, F-X. Vialard, An Interpolating Distance Between Optimal Transport and Fisher–Rao Metrics, Foundations of Computational Mathematics, 2016. [pdf]

Selection of talks

Slides often include videos that can be read with Adobe Acrobat (try to click on any image).