AIConfPaper
← Search

Emmanuel de Bezenac

13 accepted papers

2025

Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed Methods

Lise Le Boudec, Emmanuel de Bezenac, Louis Serrano, Ramon Daniel Regueiro-Espino, Yuan Yin, Patrick Gallinari
ICLR 2025poster

Physics-informed deep learning often faces optimization challenges due to the complexity of solving partial differential equations (PDEs), which involve exploring large solution spaces, require numerous iterations, and can lead to unstable training. These challenges arise particularly from the ill-c…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

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

Tim De Ryck, Florent Bonnet, Siddhartha Mishra, Emmanuel de Bezenac
ICLR 2024poster

In this paper, we investigate the behavior of gradient descent algorithms in physics-informed machine learning methods like PINNs, which minimize residuals connected to partial differential equations (PDEs). Our key result is that the difficulty in training these models is closely related to the con…

Cited by 29Source ↗PDF ↗Scholar ↗
2024

Beyond Regular Grids: Fourier-Based Neural Operators on Arbitrary Domains

Levi E. Lingsch, Mike Yan Michelis, Emmanuel de Bezenac, Sirani M. Perera, Robert K. Katzschmann, Siddhartha Mishra
ICML 2024poster

The computational efficiency of many neural operators, widely used for learning solutions of PDEs, relies on the fast Fourier transform (FFT) for performing spectral computations. As the FFT is limited to equispaced (rectangular) grids, this limits the efficiency of such neural operators when applie…

Cited by 6Source ↗PDF ↗Scholar ↗
2024

Poseidon: Efficient Foundation Models for PDEs

Maximilian Herde, Bogdan Raonic, Tobias Rohner, Roger Käppeli, Roberto Molinaro, Emmanuel de Bezenac +1
NeurIPS 2024poster

We introduce Poseidon, a foundation model for learning the solution operators of PDEs. It is based on a multiscale operator transformer, with time-conditioned layer norms that enable continuous-in-time evaluations. A novel training strategy leveraging the semi-group property of time-dependent PDEs t…

Cited by 31Source ↗PDF ↗code ↗Scholar ↗
2023

Convolutional Neural Operators for robust and accurate learning of PDEs

Bogdan Raonic, Roberto Molinaro, Tim De Ryck, Tobias Rohner, Francesca Bartolucci, Rima Alaifari +2
NeurIPS 2023poster

Although very successfully used in conventional machine learning, convolution based neural network architectures -- believed to be inconsistent in function space -- have been largely ignored in the context of learning solution operators of PDEs. Here, we present novel adaptations for convolutional n…

Cited by 52Source ↗PDF ↗code ↗Scholar ↗
2023

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

Skander Karkar, Ibrahim Ayed, Emmanuel de Bezenac, patrick gallinari
NeurIPS 2023poster

Greedy layer-wise or module-wise training of neural networks is compelling in constrained and on-device settings where memory is limited, as it circumvents a number of problems of end-to-end back-propagation. However, it suffers from a stagnation problem, whereby early layers overfit and deeper laye…

Cited by 3Source ↗PDF ↗Scholar ↗
2023

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

Francesca Bartolucci, Emmanuel de Bezenac, Bogdan Raonic, Roberto Molinaro, Siddhartha Mishra, Rima Alaifari
NeurIPS 2023poster

Recently, operator learning, or learning mappings between infinite-dimensional function spaces, has garnered significant attention, notably in relation to learning partial differential equations from data. Conceptually clear when outlined on paper, neural operators necessitate discretization in the…

Cited by 52Source ↗PDF ↗Scholar ↗
2023

Unifying GANs and Score-Based Diffusion as Generative Particle Models

Jean-Yves Franceschi, Mike Gartrell, Ludovic Dos Santos, Thibaut Issenhuth, Emmanuel de Bezenac, Mickael Chen +1
NeurIPS 2023poster

Particle-based deep generative models, such as gradient flows and score-based diffusion models, have recently gained traction thanks to their striking performance. Their principle of displacing particle distributions using differential equations is conventionally seen as opposed to the previously wi…

Cited by 26Source ↗PDF ↗code ↗Scholar ↗
2022

Mapping conditional distributions for domain adaptation under generalized target shift

Matthieu Kirchmeyer, Alain Rakotomamonjy, Emmanuel de Bezenac, patrick gallinari
ICLR 2022poster

We consider the problem of unsupervised domain adaptation (UDA) between a source and a target domain under conditional and label shift a.k.a Generalized Target Shift (GeTarS). Unlike simpler UDA settings, few works have addressed this challenging problem. Recent approaches learn domain-invariant rep…

Cited by 28Source ↗PDF ↗code ↗Scholar ↗
2021

Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

Yuan Yin, Vincent LE GUEN, Jérémie DONA, Emmanuel de Bezenac, Ibrahim Ayed, Nicolas THOME +1
ICLR 2021oral

Forecasting complex dynamical phenomena in settings where only partial knowledge of their dynamics is available is a prevalent problem across various scientific fields. While purely data-driven approaches are arguably insufficient in this context, standard physical modeling based approaches tend to…

Cited by 199Source ↗PDF ↗code ↗Scholar ↗
2021

LEADS: Learning Dynamical Systems that Generalize Across Environments

Yuan Yin, Ibrahim Ayed, Emmanuel de Bezenac, Nicolas Baskiotis, patrick gallinari
NeurIPS 2021poster

When modeling dynamical systems from real-world data samples, the distribution of data often changes according to the environment in which they are captured, and the dynamics of the system itself vary from one environment to another. Generalizing across environments thus challenges the conventional…

Cited by 45Source ↗PDF ↗code ↗Scholar ↗
2018

Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge

Emmanuel de Bezenac, Arthur Pajot, Patrick Gallinari
ICLR 2018poster

We consider the use of Deep Learning methods for modeling complex phenomena like those occurring in natural physical processes. With the large amount of data gathered on these phenomena the data intensive paradigm could begin to challenge more traditional approaches elaborated over the years in fie…

Cited by 412Source ↗PDF ↗code ↗Scholar ↗