meyer scetbon
16 papers · 2019–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Academic Marathon (6) π Cross-Pollinator (12)
πΊοΈ
Taxonomy Completionist
(25)
π
Conference Polyglot
(3)
π
Century Club
(16)
π₯
Unstoppable
(7)
ποΈ
Keyword Collector
(72)
Conferences
ICML (8)
AISTATS (4)
NIPS (4)
Top co-authors
Keywords
optimal transport
(6)
entropic regularization
(5)
kernel methods
(3)
entropy regularization
(3)
reproducing kernel hilbert space
(2)
approximation error
(2)
low-rank approximation
(2)
computational complexity
(1)
point cloud
(1)
feature extraction
(1)
distribution comparison
(1)
gradient descent
(1)
linear programming
(1)
kernel matrix
(1)
early stopping
(1)
two-sample test
(1)
distribution testing
(1)
statistical testing
(1)
spectral analysis
(1)
linear regression
(1)
Papers
SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
ICML 2025
A Fixed-Point Approach for Causal Generative Modeling
ICML 2024
Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms
ICML 2024
Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond
AISTATS 2023
Unbalanced Low-rank Optimal Transport Solvers
NIPS 2023
Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs
ICML 2022
Low-rank Optimal Transport: Approximation, Statistics and Debiasing
NIPS 2022
Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Rates
AISTATS 2022
An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings
ICML 2022
Mixed Nash Equilibria in the Adversarial Examples Game
ICML 2021
Low-Rank Sinkhorn Factorization
ICML 2021
Equitable and Optimal Transport with Multiple Agents
AISTATS 2021
A Spectral Analysis of Dot-product Kernels
AISTATS 2021
Harmonic Decompositions of Convolutional Networks
ICML 2020
Linear Time Sinkhorn Divergences using Positive Features
NIPS 2020
Comparing distributions: $\ell_1$ geometry improves kernel two-sample testing
NIPS 2019