← Authors

Gabriel Peyré

43 papers · 2014–2025 · 5 conferences · across top CS/AI conferences

Achievements

🏃 Academic Marathon (11) 🌍 Conference Polyglot (5) 🐝 Cross-Pollinator (11) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (18) 🌈 Renaissance Researcher (6) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🤝 Dynamic Duo (11) 🏆 Keyword Champion (2) 🔬 Deep Specialist (23) 🧬 Topic Evolution ⚡ Prolific Year (5) ❓ The Questioner (4) 🗃️ Keyword Collector (169) 📈 Trend Setter 💎 Century Club (43) 🔥 Unstoppable (8)

Conferences

NIPS (14) ICML (13) AISTATS (12) ICLR (3) COLT (1)

Top co-authors

Marco Cuturi (11) Pierre Ablin (7) Francois-Xavier Vialard (5) Jalal Fadili (5) Mathieu Blondel (5) Sibylle Marcotte (3) Clarice Poon (3) Remi Gribonval (3) Thibault Sejourne (3) Aude Genevay (3)

Keywords

optimal transport (14) sinkhorn algorithm (6) entropic regularization (6) wasserstein distance (6) sinkhorn divergence (4) gromov-wasserstein distance (3) entropy regularization (3) kernel methods (3) gradient flow (2) generative model (2) residual network (2) metric learning (2) maximum mean discrepancy (2) wasserstein metric (2) bilevel optimization (2) point cloud (2) sample complexity (2) gradient descent (2) support recovery (2) convex optimization (2)

Papers

Transformative or Conservative? Conservation laws for ResNets and Transformers ICML 2025
Transformers are Universal In-context Learners ICLR 2025
Towards Understanding the Universality of Transformers for Next-Token Prediction ICLR 2025
How Smooth Is Attention? ICML 2024
How do Transformers Perform In-Context Autoregressive Learning ? ICML 2024
Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows ICML 2024
Structured Transforms Across Spaces with Cost-Regularized Optimal Transport AISTATS 2024
Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization AISTATS 2024
Sparsistency for inverse optimal transport ICLR 2024
Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective ICML 2023
Abide by the law and follow the flow: conservation laws for gradient flows NIPS 2023
Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe AISTATS 2022
On global convergence of ResNets: From finite to infinite width using linear parameterization NIPS 2022
Do Residual Neural Networks discretize Neural Ordinary Differential Equations? NIPS 2022
Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs ICML 2022
Unsupervised Ground Metric Learning Using Wasserstein Singular Vectors ICML 2022
Randomized Stochastic Gradient Descent Ascent AISTATS 2022
Sinkformers: Transformers with Doubly Stochastic Attention AISTATS 2022
Fast and accurate optimization on the orthogonal manifold without retraction AISTATS 2022
Smooth Bilevel Programming for Sparse Regularization NIPS 2021
Low-Rank Sinkhorn Factorization ICML 2021
Momentum Residual Neural Networks ICML 2021
The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation NIPS 2021
Wasserstein Control of Mirror Langevin Monte Carlo COLT 2020
Online Sinkhorn: Optimal Transport distances from sample streams NIPS 2020
Faster Wasserstein Distance Estimation with the Sinkhorn Divergence NIPS 2020
Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form NIPS 2020
Super-efficiency of automatic differentiation for functions defined as a minimum ICML 2020
Interpolating between Optimal Transport and MMD using Sinkhorn Divergences AISTATS 2019
Sample Complexity of Sinkhorn Divergences AISTATS 2019
Stochastic Deep Networks ICML 2019
Geometric Losses for Distributional Learning ICML 2019
Support Localization and the Fisher Metric for off-the-grid Sparse Regularization AISTATS 2019
Model Consistency for Learning with Mirror-Stratifiable Regularizers AISTATS 2019
Universal Invariant and Equivariant Graph Neural Networks NIPS 2019
Learning Generative Models with Sinkhorn Divergences AISTATS 2018
Fast Dictionary Learning with a Smoothed Wasserstein Loss AISTATS 2016
Gromov-Wasserstein Averaging of Kernel and Distance Matrices ICML 2016
Stochastic Optimization for Large-scale Optimal Transport NIPS 2016
A Multi-step Inertial Forward-Backward Splitting Method for Non-convex Optimization NIPS 2016
Sparse Support Recovery with Non-smooth Loss Functions NIPS 2016
Biologically Inspired Dynamic Textures for Probing Motion Perception NIPS 2015
Local Linear Convergence of Forward--Backward under Partial Smoothness NIPS 2014