Emmanuel de Bézenac

According to our database, Emmanuel de Bézenac authored at least 25 papers between 2018 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

An operator preconditioning perspective on training in physics-informed machine learning.

Tim De Ryck, Florent Bonnet, Siddhartha Mishra, Emmanuel de Bézenac

CoRR, 2023

Are Neural Operators Really Neural Operators? Frame Theory Meets Operator Learning.

Francesca Bartolucci, Emmanuel de Bézenac, Bogdan Raonic, Roberto Molinaro, Siddhartha Mishra, Rima Alaifari

CoRR, 2023

Convolutional Neural Operators.

Bogdan Raonic, Roberto Molinaro, Tobias Rohner, Siddhartha Mishra, Emmanuel de Bézenac

CoRR, 2023

Convolutional Neural Operators for robust and accurate learning of PDEs.

Bogdan Raonic, Roberto Molinaro, Tim De Ryck, Tobias Rohner, Francesca Bartolucci, Rima Alaifari, Siddhartha Mishra, Emmanuel de Bézenac

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Module-wise Training of Neural Networks via the Minimizing Movement Scheme.

Skander Karkar, Ibrahim Ayed, Emmanuel de Bézenac, Patrick Gallinari

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Unifying GANs and Score-Based Diffusion as Generative Particle Models.

Jean-Yves Franceschi, Mike Gartrell, Ludovic Dos Santos, Thibaut Issenhuth, Emmanuel de Bézenac, Mickaël Chen, Alain Rakotomamonjy

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learning.

Francesca Bartolucci, Emmanuel de Bézenac, Bogdan Raonic, Roberto Molinaro, Siddhartha Mishra, Rima Alaifari

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Modelling spatiotemporal dynamics from Earth observation data with neural differential equations.

Ibrahim Ayed, Emmanuel de Bézenac, Arthur Pajot, Patrick Gallinari

Mach. Learn., 2022

Module-wise Training of Residual Networks via the Minimizing Movement Scheme.

Skander Karkar, Ibrahim Ayed, Emmanuel de Bézenac, Patrick Gallinari

CoRR, 2022

A Neural Tangent Kernel Perspective of GANs.

Jean-Yves Franceschi, Emmanuel de Bézenac, Ibrahim Ayed, Mickaël Chen, Sylvain Lamprier, Patrick Gallinari

Proceedings of the International Conference on Machine Learning, 2022

Mapping conditional distributions for domain adaptation under generalized target shift.

Matthieu Kirchmeyer, Alain Rakotomamonjy, Emmanuel de Bézenac, Patrick Gallinari

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Modeling Physical Processes with Deep Learning: A Dynamical Systems Approach. (Modélisation de Processus Physique avec de l'Apprentissage Profond).

Emmanuel de Bézenac

PhD thesis, 2021

CycleGAN Through the Lens of (Dynamical) Optimal Transport.

Emmanuel de Bézenac, Ibrahim Ayed, Patrick Gallinari

Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2021

LEADS: Learning Dynamical Systems that Generalize Across Environments.

Yuan Yin, Ibrahim Ayed, Emmanuel de Bézenac, Nicolas Baskiotis, Patrick Gallinari

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting.

Yuan Yin, Vincent Le Guen, Jérémie Donà, Emmanuel de Bézenac, Ibrahim Ayed, Nicolas Thome, Patrick Gallinari

Proceedings of the 9th International Conference on Learning Representations, 2021

Learning Dynamical Systems across Environments.

Yuan Yin, Ibrahim Ayed, Emmanuel de Bézenac, Patrick Gallinari

Proceedings of the AAAI 2021 Spring Symposium on Combining Artificial Intelligence and Machine Learning with Physical Sciences, Stanford, CA, USA, March 22nd - to, 2021

2020

A Principle of Least Action for the Training of Neural Networks.

Skander Karkar, Ibrahim Ayed, Emmanuel de Bézenac, Patrick Gallinari

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2020

Deep Rao-Blackwellised Particle Filters for Time Series Forecasting.

Richard Kurle, Syama Sundar Rangapuram, Emmanuel de Bézenac, Stephan Günnemann, Jan Gasthaus

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Normalizing Kalman Filters for Multivariate Time Series Analysis.

Emmanuel de Bézenac, Syama Sundar Rangapuram, Konstantinos Benidis, Michael Bohlke-Schneider, Richard Kurle, Lorenzo Stella, Hilaf Hasson, Patrick Gallinari, Tim Januschowski

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Learning the Spatio-Temporal Dynamics of Physical Processes from Partial Observations.

Ibrahim Ayed, Emmanuel de Bézenac, Arthur Pajot, Patrick Gallinari

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

Unsupervised Adversarial Image Inpainting.

Arthur Pajot, Emmanuel de Bézenac, Patrick Gallinari

CoRR, 2019

Optimal Unsupervised Domain Translation.

Emmanuel de Bézenac, Ibrahim Ayed, Patrick Gallinari

CoRR, 2019

Learning Dynamical Systems from Partial Observations.

Ibrahim Ayed, Emmanuel de Bézenac, Arthur Pajot, Julien Brajard, Patrick Gallinari

CoRR, 2019

Unsupervised Adversarial Image Reconstruction.

Arthur Pajot, Emmanuel de Bézenac, Patrick Gallinari

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge.

Emmanuel de Bézenac, Arthur Pajot, Patrick Gallinari

Proceedings of the 6th International Conference on Learning Representations, 2018