I am a post-doctoral research at École Normale Supérieure, Paris, in the laboratory of Gabriel Peyré. I hold a Ph.D. in machine learning, prepared in Inria Parietal team, from 2015 to 2018.

I am currently working in structured prediction, optimal transport and game theory.

My Ph.D. was obtained under the supervision of Gaël Varoquaux, Julien Mairal and Bertrand Thirion. I developed new stochastic algorithms and multi-task models for terabyte sized fMRI dataset analysis.

My detailed resume can be found here. Here are more details on the research and software that I do.


  • 05/19 Our ICML 2019 paper Geometric Losses for Distributional Learning (joint work with Mathieu Blondel and Gabriel Peyré) is available
  • 03/19 I am visiting Joan Bruna Lab at NYU CIMS for three months.
  • 01/19 Slides for an extended presentation of Differentiable Dynamic Programming for Stuctured Prediction and Attention Paper
  • 11/18 I started working as a post-doct with Gabriel Peyré, in ENS, Paris
  • 10/18 Preprint of our work Extracting Universal Representations of Cognition across Brain-Imaging Studies on multi-dataset decoding for functional MRI data
  • 09/18 I defended my PhD thesis (Slides, Thesis) at NeuroSpin.
  • 09/18 Our paper Differentiable Dynamic Programming for Stuctured Prediction and Attention was accepted at ICML 2018. Paper. Presented on the 07/12/18 at Stockholm Slides
  • 11/17 Our NIPS 2017 paper Learning Neural Representations of Human Cognition across Many fMRI Studies is available.

Arthur Mensch © 2019. All rights reserved.

Powered by Hydejack v8.4.0