Publications de Clément Hongler

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Wulfram Gerstner, Clément Hongler, Johanni Michael Brea, Francesco Spadaro, Berfin Simsek, Arthur Jacot

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with

L

layers of minimal widths

r_1^*, \ldots, r_{L-1}^*

reaches a zero-loss minimum at $ r_1^*! \c ...

2021

Clément Hongler

Graph Chatbot

Chattez avec Graph Search

Conformal Field Theory at the Lattice Level: Discrete Complex Analysis and Virasoro Structure

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Neural Tangent Kernel: Convergence and Generalization in Neural Networks (Invited Paper)

Scaling description of generalization with number of parameters in deep learning

Ising Model: Local Spin Correlations and Conformal Invariance

The Scaling Limit Of Critical Ising Interfaces Is Cle3

Conformal invariance of crossing probabilities for the Ising model with free boundary conditions

Crossing Probabilities in Topological Rectangles for the Critical Planar FK-Ising model

Conformal Invariance of Spin Pattern Probabilities in the Planar Ising Model

Conformal Invariance of Spin Correlations in the Planar Ising Model

Conformal Field Theory at the Lattice Level: Discrete Complex Analysis and Virasoro Structure

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Scaling description of generalization with number of parameters in deep learning

Neural Tangent Kernel: Convergence and Generalization in Neural Networks (Invited Paper)

The Scaling Limit Of Critical Ising Interfaces Is Cle3

Ising Model: Local Spin Correlations and Conformal Invariance

Crossing Probabilities in Topological Rectangles for the Critical Planar FK-Ising model

Conformal invariance of crossing probabilities for the Ising model with free boundary conditions

Conformal Invariance of Spin Pattern Probabilities in the Planar Ising Model

Conformal Invariance of Spin Correlations in the Planar Ising Model