| Align, then memorise: the dynamics of learning with feedback alignment M Refinetti, S d’Ascoli, R Ohana, S Goldt International Conference on Machine Learning, 8925-8935, 2021 | 60 | 2021 |
| xval: A continuous number encoding for large language models S Golkar, M Pettee, M Eickenberg, A Bietti, M Cranmer, G Krawezik, ... arXiv preprint arXiv:2310.02989, 2023 | 55 | 2023 |
| Multiple Physics Pretraining for Spatiotemporal Surrogate Models M McCabe, B Régaldo-Saint Blancard, LH Parker, R Ohana, M Cranmer, ... Advances in Neural Information Processing Systems 38, 2024 | 53* | 2024 |
| AstroCLIP: a cross-modal foundation model for galaxies L Parker, F Lanusse, S Golkar, L Sarra, M Cranmer, A Bietti, M Eickenberg, ... Monthly Notices of the Royal Astronomical Society 531 (4), 4990-5011, 2024 | 40* | 2024 |
| Reservoir Computing meets Recurrent Kernels and Structured Transforms J Dong, R Ohana, M Rafayelyan, F Krzakala Advances in Neural Information Processing Systems 33 (Oral), 2020 | 35 | 2020 |
| Kernel computations from large-scale random features obtained by optical processing units R Ohana, J Wacker, J Dong, S Marmin, F Krzakala, M Filippone, L Daudet ICASSP 2020-2020 IEEE international conference on acoustics, speech and …, 2020 | 33 | 2020 |
| Adversarial robustness by design through analog computing and synthetic gradients A Cappelli, R Ohana, J Launay, L Meunier, I Poli, F Krzakala ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 13 | 2022 |
| Photonic Differential Privacy with Direct Feedback Alignment R Ohana, HJM Ruiz, J Launay, A Cappelli, I Poli, L Ralaivola, ... Advances in Neural Information Processing Systems 35, 2021 | 13 | 2021 |
| Lighton optical processing unit: Scaling-up AI and HPC with a non von neumann co-processor C Brossollet, A Cappelli, I Carron, C Chaintoutis, A Chatelain, L Daudet, ... arXiv preprint arXiv:2107.11814, 2021 | 11 | 2021 |
| Shedding a PAC-Bayesian light on adaptive sliced-Wasserstein distances R Ohana, K Nadjahi, A Rakotomamonjy, L Ralaivola International Conference on Machine Learning, 26451-26473, 2023 | 9 | 2023 |
| Photonic co-processors in HPC: using LightOn OPUs for Randomized Numerical Linear Algebra D Hesslow, A Cappelli, I Carron, L Daudet, R Lafargue, K Müller, ... arXiv preprint arXiv:2104.14429, 2021 | 9 | 2021 |
| Momo: Momentum models for adaptive learning rates F Schaipp, R Ohana, M Eickenberg, A Defazio, RM Gower International Conference on Machine Learning, 43542-43570, 2024 | 8 | 2024 |
| Method and system for machine learning using optical data I Poli, J Launay, K Müller, G Pariente, I Carron, L Daudet, R Ohana, ... US Patent 11,574,178, 2023 | 8 | 2023 |
| Complex-to-Real Sketches for Tensor Products with Applications to the Polynomial Kernel J Wacker, R Ohana, M Filippone International Conference on Artificial Intelligence and Statistics, 5181-5212, 2023 | 7* | 2023 |
| ROPUST: improving robustness through fine-tuning with photonic processors and synthetic gradients A Cappelli, J Launay, L Meunier, R Ohana, I Poli arXiv preprint arXiv:2108.04217, 2021 | 7 | 2021 |
| Impact of epitaxial strain on the topological-nontopological phase diagram and semimetallic behavior of InAs/GaSb composite quantum wells H Irie, T Akiho, F Couëdo, R Ohana, K Suzuki, K Onomitsu, K Muraki Physical Review B 101 (7), 075433, 2020 | 6 | 2020 |
| The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning R Ohana, M McCabe, LT Meyer, R Morel, FJ Agocs, M Beneitez, M Berger, ... The Thirty-eight Conference on Neural Information Processing Systems …, 2024 | 3 | 2024 |
| Listening to the Noise: Blind Denoising with Gibbs Diffusion D Heurtel-Depeiges, CC Margossian, R Ohana, BRS Blancard International Conference on Machine Learning, 18284-18304, 2024 | 3* | 2024 |
| Linear Optical Random Projections Without Holography R Ohana, D Hesslow, D Brunner, S Gigan, K Müller Optics Express, 2023 | 3 | 2023 |
| Optical training of large-scale Transformers and deep neural networks with direct feedback alignment Z Wang, K Müller, M Filipovich, J Launay, R Ohana, G Pariente, ... arXiv preprint arXiv:2409.12965, 2024 | 1 | 2024 |
Miles CranmerUniversity of CambridgeE-mail confirmado em cam.ac.uk