Picture for Gabriel Peyré

Gabriel Peyré

CNRS and ENS-PSL

Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows

Add code
May 21, 2024
Viaarxiv icon

Understanding the training of infinitely deep and wide ResNets with Conditional Optimal Transport

Mar 19, 2024
Viaarxiv icon

Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization

Add code
Feb 26, 2024
Figure 1 for Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization
Figure 2 for Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization
Figure 3 for Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization
Figure 4 for Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization
Viaarxiv icon

How do Transformers perform In-Context Autoregressive Learning?

Add code
Feb 08, 2024
Viaarxiv icon

Understanding the Regularity of Self-Attention with Optimal Transport

Dec 22, 2023
Figure 1 for Understanding the Regularity of Self-Attention with Optimal Transport
Figure 2 for Understanding the Regularity of Self-Attention with Optimal Transport
Viaarxiv icon

Structured Transforms Across Spaces with Cost-Regularized Optimal Transport

Nov 23, 2023
Viaarxiv icon

Abide by the Law and Follow the Flow: Conservation Laws for Gradient Flows

Add code
Jun 30, 2023
Viaarxiv icon

Test like you Train in Implicit Deep Learning

Add code
May 24, 2023
Figure 1 for Test like you Train in Implicit Deep Learning
Figure 2 for Test like you Train in Implicit Deep Learning
Figure 3 for Test like you Train in Implicit Deep Learning
Figure 4 for Test like you Train in Implicit Deep Learning
Viaarxiv icon

Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective

Add code
Feb 06, 2023
Figure 1 for Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective
Figure 2 for Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective
Figure 3 for Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective
Figure 4 for Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective
Viaarxiv icon

Unbalanced Optimal Transport, from Theory to Numerics

Nov 16, 2022
Figure 1 for Unbalanced Optimal Transport, from Theory to Numerics
Figure 2 for Unbalanced Optimal Transport, from Theory to Numerics
Figure 3 for Unbalanced Optimal Transport, from Theory to Numerics
Figure 4 for Unbalanced Optimal Transport, from Theory to Numerics
Viaarxiv icon