| Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge E de Bézenac, A Pajot, P Gallinari arXiv preprint arXiv:1711.07970, 2017 | 185 | 2017 |
| Learning dynamical systems from partial observations I Ayed, E de Bézenac, A Pajot, J Brajard, P Gallinari arXiv preprint arXiv:1902.11136, 2019 | 51 | 2019 |
| Augmenting physical models with deep networks for complex dynamics forecasting Y Yin, V Le Guen, J Dona, E de Bézenac, I Ayed, N Thome, P Gallinari Journal of Statistical Mechanics: Theory and Experiment 2021 (12), 124012, 2021 | 29 | 2021 |
| Normalizing kalman filters for multivariate time series analysis E de Bézenac, SS Rangapuram, K Benidis, M Bohlke-Schneider, R Kurle, ... Advances in Neural Information Processing Systems 33, 2995-3007, 2020 | 28 | 2020 |
| Unsupervised adversarial image reconstruction A Pajot, E De Bézenac, P Gallinari International conference on learning representations, 2018 | 25 | 2018 |
| Deep rao-blackwellised particle filters for time series forecasting R Kurle, SS Rangapuram, E de Bézenac, S Günnemann, J Gasthaus Advances in Neural Information Processing Systems 33, 15371-15382, 2020 | 16 | 2020 |
| Optimal unsupervised domain translation E de Bézenac, I Ayed, P Gallinari arXiv preprint arXiv:1906.01292, 2019 | 11 | 2019 |
| Learning the spatio-temporal dynamics of physical processes from partial observations I Ayed, E de Bézenac, A Pajot, P Gallinari ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 9 | 2020 |
| A neural tangent kernel perspective of gans JY Franceschi, E de Bézenac, I Ayed, M Chen, S Lamprier, P Gallinari arXiv preprint arXiv:2106.05566, 2021 | 5 | 2021 |
| Cyclegan through the lens of (dynamical) optimal transport E Bézenac, I Ayed, P Gallinari Joint European Conference on Machine Learning and Knowledge Discovery in …, 2021 | 3 | 2021 |
| A principle of least action for the training of neural networks S Karkar, I Ayed, E Bézenac, P Gallinari Joint European Conference on Machine Learning and Knowledge Discovery in …, 2020 | 3 | 2020 |
| Learning Partially Observed PDE Dynamics with Neural Networks I Ayed, E de Bézenac, A Pajot, P Gallinari | 3 | 2018 |
| Unsupervised adversarial image inpainting A Pajot, E de Bezenac, P Gallinari arXiv preprint arXiv:1912.12164, 2019 | 2 | 2019 |
| Towards a hybrid approach to physical process modeling E De Bézenac, A Pajot, P Gallinari Technical report, 2017 | 2 | 2017 |
| LEADS: Learning Dynamical Systems that Generalize Across Environments Y Yin, I Ayed, E de Bézenac, N Baskiotis, P Gallinari Advances in Neural Information Processing Systems 34, 2021 | 1 | 2021 |
| Mapping conditional distributions for domain adaptation under generalized target shift M Kirchmeyer, A Rakotomamonjy, E de Bezenac, P Gallinari arXiv preprint arXiv:2110.15057, 2021 | 1 | 2021 |
| Modelling spatiotemporal dynamics from Earth observation data with neural differential equations I Ayed, E de Bézenac, A Pajot, P Gallinari Machine Learning, 1-32, 2022 | | 2022 |
| Block-wise Training of Residual Networks via the Minimizing Movement Scheme S Karkar, I Ayed, E de Bézenac, P Gallinari | | 2022 |
| Modeling physical processes with deep learning: a dynamical systems approach E Bézenac Sorbonne université, 2021 | | 2021 |
| A NEURAL TANGENT KERNEL PERSPECTIVE OF GANS I GdR, JY Franceschi, E de Bézenac, I Ayed, M Chen, S Lamprier, ... | | 2021 |
