Suivre
Pierre Marion
Pierre Marion
Adresse e-mail validée de epfl.ch - Page d'accueil
Titre
Citée par
Citée par
Année
Framing RNN as a kernel method: A neural ODE approach
A Fermanian, P Marion, JP Vert, G Biau
Advances in Neural Information Processing Systems 34, 3121-3134, 2021
262021
Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs
P Marion, PK Nowak, F Piccinno
EMNLP 2021, 8813–8829, 2021
212021
A tool for custom construction of QMC and RQMC point sets
P L’Ecuyer, P Marion, M Godin, F Puchhammer
International Conference on Monte Carlo and Quasi-Monte Carlo Methods in …, 2020
202020
Scaling resnets in the large-depth regime
P Marion, A Fermanian, G Biau, JP Vert
arXiv preprint arXiv:2206.06929, 2022
112022
An algorithm to compute the t-value of a digital net and of its projections
P Marion, M Godin, P L’Ecuyer
Journal of Computational and Applied Mathematics 371, 112669, 2020
102020
Generalization bounds for neural ordinary differential equations and deep residual networks
P Marion
Advances in Neural Information Processing Systems 36, 2023
92023
Implicit regularization of deep residual networks towards neural ODEs
P Marion, YH Wu, ME Sander, G Biau
The Twelfth International Conference on Learning Representations, 2023
62023
Leveraging the two-timescale regime to demonstrate convergence of neural networks
P Marion, R Berthier
Advances in Neural Information Processing Systems 36, 2023
42023
Implicit Diffusion: Efficient Optimization through Stochastic Sampling
P Marion, A Korba, P Bartlett, M Blondel, V De Bortoli, A Doucet, ...
arXiv preprint arXiv:2402.05468, 2024
12024
Deep linear networks for regression are implicitly regularized towards flat minima
P Marion, L Chizat
arXiv preprint arXiv:2405.13456, 2024
2024
Mathematics of deep learning: generalization, optimization, continuous-time models
P Marion
Sorbonne Université, 2023
2023
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–11