Meyer Scetbon

According to our database, Meyer Scetbon authored at least 30 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension.

Wenbo Gong, Meyer Scetbon, Chao Ma, Edward Meeds

CoRR, February, 2025

Gradient Multi-Normalization for Stateless and Scalable LLM Training.

Meyer Scetbon, Chao Ma, Wenbo Gong, Edward Meeds

CoRR, February, 2025

2024

Deep End-to-end Causal Inference.

Tomas Geffner, Javier Antorán, Adam Foster, Wenbo Gong, Chao Ma, Emre Kiciman, Amit Sharma, Angus Lamb, Martin Kukla, Nick Pawlowski, Agrin Hilmkil, Joel Jennings, Meyer Scetbon, Miltiadis Allamanis, Cheng Zhang

Trans. Mach. Learn. Res., 2024

SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training.

Chao Ma, Wenbo Gong, Meyer Scetbon, Edward Meeds

CoRR, 2024

Low-Rank Correction for Quantized LLMs.

Meyer Scetbon, James Hensman

CoRR, 2024

Zero-Shot Learning of Causal Models.

Divyat Mahajan, Jannes Gladrow, Agrin Hilmkil, Cheng Zhang, Meyer Scetbon

CoRR, 2024

FiP: a Fixed-Point Approach for Causal Generative Modeling.

Meyer Scetbon, Joel Jennings, Agrin Hilmkil, Cheng Zhang, Chao Ma

CoRR, 2024

The Essential Role of Causality in Foundation World Models for Embodied AI.

Tarun Gupta, Wenbo Gong, Chao Ma, Nick Pawlowski, Agrin Hilmkil, Meyer Scetbon, Ade Famoti, Ashley Juan Llorens, Jianfeng Gao, Stefan Bauer, Danica Kragic, Bernhard Schölkopf, Cheng Zhang

CoRR, 2024

A Fixed-Point Approach for Causal Generative Modeling.

Meyer Scetbon, Joel Jennings, Agrin Hilmkil, Cheng Zhang, Chao Ma

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms.

Elvis Dohmatob, Meyer Scetbon

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Robust Linear Regression: Phase-Transitions and Precise Tradeoffs for General Norms.

Elvis Dohmatob, Meyer Scetbon

CoRR, 2023

Polynomial-Time Solvers for the Discrete ∞-Optimal Transport Problems.

Meyer Scetbon

CoRR, 2023

Unbalanced Low-rank Optimal Transport Solvers.

Meyer Scetbon, Michal Klein, Giovanni Palla, Marco Cuturi

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond.

Meyer Scetbon, Elvis Dohmatob

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Low-rank Optimal Transport: Approximation, Statistics and Debiasing.

Meyer Scetbon, Marco Cuturi

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs.

Meyer Scetbon, Gabriel Peyré, Marco Cuturi

Proceedings of the International Conference on Machine Learning, 2022

An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings.

Meyer Scetbon, Laurent Meunier, Yaniv Romano

Proceedings of the International Conference on Machine Learning, 2022

Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Rates.

Nicholas J. Irons, Meyer Scetbon, Soumik Pal, Zaïd Harchaoui

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Deep K-SVD Denoising.

Meyer Scetbon, Michael Elad, Peyman Milanfar

IEEE Trans. Image Process., 2021

An 𝓁^p-based Kernel Conditional Independence Test.

Meyer Scetbon, Laurent Meunier, Yaniv Romano

CoRR, 2021

Low-Rank Sinkhorn Factorization.

Meyer Scetbon, Marco Cuturi, Gabriel Peyré

Proceedings of the 38th International Conference on Machine Learning, 2021

Mixed Nash Equilibria in the Adversarial Examples Game.

Laurent Meunier, Meyer Scetbon, Rafael Pinot, Jamal Atif, Yann Chevaleyre

Proceedings of the 38th International Conference on Machine Learning, 2021

Equitable and Optimal Transport with Multiple Agents.

Meyer Scetbon, Laurent Meunier, Jamal Atif, Marco Cuturi

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

A Spectral Analysis of Dot-product Kernels.

Meyer Scetbon, Zaïd Harchaoui

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Handling Multiple Costs in Optimal Transport: Strong Duality and Efficient Computation.

Meyer Scetbon, Laurent Meunier, Jamal Atif, Marco Cuturi

CoRR, 2020

Risk Bounds for Multi-layer Perceptrons through Spectra of Integral Operators.

Meyer Scetbon, Zaïd Harchaoui

CoRR, 2020

Linear Time Sinkhorn Divergences using Positive Features.

Meyer Scetbon, Marco Cuturi

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Harmonic Decompositions of Convolutional Networks.

Meyer Scetbon, Zaïd Harchaoui

Proceedings of the 37th International Conference on Machine Learning, 2020

2019

Comparing distributions: 𝓁₁ geometry improves kernel two-sample testing.

Meyer Scetbon, Gaël Varoquaux

CoRR, 2019

Comparing distributions: 퓁₁ geometry improves kernel two-sample testing.

Meyer Scetbon, Gaël Varoquaux

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019