Meyer Scetbon

Meyer Scetbon

Quantitative Researcher at Citadel Securities

Publications

PhD thesis:

Advances in Optimal Transport: Low-Rank Structures and Applications in Machine Learning
Meyer Scetbon.
Best Thesis Award in Mathematics, Institut Polytechnique de Paris.
manuscript

Published papers:

A Fixed-Point Approach for Causal Generative Modeling
Meyer Scetbon, Joel Jennings, Agrin Himlkin, Cheng Zhang, Chao Ma.
International Conference on Machine Learning (ICML 2024).
paper code poster

Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms
Elvis Dohmatob, Meyer Scetbon.
International Conference on Machine Learning (ICML 2024).
paper

Deep End-to-end Causal Inference
Tomas Geffner et al.
Transactions on Machine Learning Research (TMLR 2024).
paper code

Unbalanced Low-rank Optimal Transport Solvers
Meyer Scetbon*, Michal Klein*, Giovanni Palla, Marco Cuturi.
Neural Information Processing Systems (NeurIPS 2023).
paper code

Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond
Meyer Scetbon, Elvis Dohmatob.
Artificial Intelligence and Statistics (AISTATS 2023).
paper

Low-rank Optimal Transport: Approximation, Statistics and Debiasing
Meyer Scetbon, Marco Cuturi.
Neural Information Processing Systems (NeurIPS 2022).
paper

An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings
Meyer Scetbon*, Laurent Meunier*, Yaniv Romano.
International Conference on Machine Learning (ICML 2022).
paper code poster slides

Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs
Meyer Scetbon, Gabriel Peyré, Marco Cuturi.
International Conference on Machine Learning (ICML 2022).
paper code poster slides

Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Rates
Nicholas J. Irons, Meyer Scetbon, Soumik Pal, Zaid Harchaoui.
Artificial Intelligence and Statistics (AISTATS 2022).
paper

Deep K-SVD Denoising
Meyer Scetbon, Michael Elad, Peyman Milanfar.
IEEE Transactions on Image Processing.
paper code

Low-Rank Sinkhorn Factorization
Meyer Scetbon, Marco Cuturi, Gabriel Peyré.
International Conference on Machine Learning (ICML 2021).
paper code poster slides

Mixed Nash Equilibria in the Adversarial Examples Game
Laurent Meunier*, Meyer Scetbon*, Rafael Pinot, Jamal Atif, Yann Chevaleyre.
International Conference on Machine Learning (ICML 2021).
paper poster slides

Equitable and Optimal Transport with Multiple Agents
Meyer Scetbon*, Laurent Meunier*, Jamal Atif, Marco Cuturi.
Artificial Intelligence and Statistics (AISTATS 2021).
paper code poster slides

A Spectral Analysis of Dot-product Kernels
Meyer Scetbon, Zaid Harchaoui.
Artificial Intelligence and Statistics (AISTATS 2021).
paper poster slides

Linear Time Sinkhorn Divergences using Positive Features
Meyer Scetbon, Marco Cuturi.
Neural Information Processing Systems (NeurIPS 2020).
paper code poster slides

Harmonic Decompositions of Convolutional Networks
Meyer Scetbon, Zaid Harchaoui.
International Conference on Machine Learning (ICML 2020).
paper slides

Comparing distributions: l1 geometry improves kernel two-sample testing
Meyer Scetbon, Gaël Varoquaux.
Spotlight at Neural Information Processing Systems (NeurIPS 2019).
paper code poster slides

Preprint papers:

Zero-Shot Learning of Causal Models
Divyat Mahajan*, Jannes Gladrow, Agrin Hilmkil, Cheng Zhang, Meyer Scetbon*.
paper code

Low-Rank Correction for Quantized LLMs
Meyer Scetbon, James Hensman.
paper

The Essential Role of Causality in Foundation World Models for Embodied AI
Causica Team et al.
paper

Polynomial-Time Solvers for the Discrete $\infty$-Optimal Transport Problems
Meyer Scetbon.
paper

Reviewing service: