| Deep learning generalizes because the parameter-function map is biased towards simple functions G Valle-Perez, CQ Camargo, AA Louis arXiv preprint arXiv:1805.08522, 2018 | 231 | 2018 |
| Is SGD a Bayesian sampler? Well, almost C Mingard, G Valle-Pérez, J Skalse, AA Louis Journal of Machine Learning Research 22 (79), 1-64, 2021 | 56 | 2021 |
| Transflower: probabilistic autoregressive dance generation with multimodal attention G Valle-Pérez, GE Henter, J Beskow, A Holzapfel, PY Oudeyer, ... ACM Transactions on Graphics (TOG) 40 (6), 1-14, 2021 | 51 | 2021 |
| Neural networks are a priori biased towards boolean functions with low entropy C Mingard, J Skalse, G Valle-Pérez, D Martínez-Rubio, V Mikulik, ... arXiv preprint arXiv:1909.11522, 2019 | 33 | 2019 |
| Generalization bounds for deep learning G Valle-Pérez, AA Louis arXiv preprint arXiv:2012.04115, 2020 | 31 | 2020 |
| Deep neural networks have an inbuilt Occam’s razor C Mingard, H Rees, G Valle-Pérez, AA Louis Nature Communications 16 (1), 220, 2025 | 11 | 2025 |
| Language-biased image classification: evaluation based on semantic representations Y Lemesle, M Sawayama, G Valle-Perez, M Adolphe, H Sauzéon, ... arXiv preprint arXiv:2201.11014, 2022 | 10 | 2022 |
| Louis G Valle-Pérez, CQ Camargo, A Ard Deep learning generalizes because the parameter-function map is biased …, 2018 | 10 | 2018 |
| Louis. Generalization bounds for deep learning G Valle-Pérez, A Ard arXiv preprint arXiv:2012.04115, 2020 | 9 | 2020 |
| Double-descent curves in neural networks: a new perspective using Gaussian processes O El Harzli, BC Grau, G Valle-Pérez, AA Louis Proceedings of the AAAI Conference on Artificial Intelligence 38 (10), 11856 …, 2024 | 7 | 2024 |
| Why Flatness Correlates With Generalization For Deep Neural Networks S Zhang, I Reid, G Pérez, A Louis arXiv preprint arXiv:2103.06219, 2021 | 4 | 2021 |
| Bounds on learning with power-law priors S Ridout, I Nemenman, A Louis, C Mingard, R Grabarczyk, K Dingle, ... Bulletin of the American Physical Society, 2024 | 1 | 2024 |
| Evaluating language-biased image classification based on semantic representations. Y Lemesle, M Sawayama, GV Pérez, M Adolphe, H Sauzéon, PY Oudeyer CoRR, 2022 | | 2022 |
| Generic predictions of output probability based on complexities of inputs and outputs D Kamaludin, GV Pérez, AA Louis Scientific Reports (Nature Publisher Group) 10 (1), 2020 | | 2020 |
| Simplicity bias in the parameter-function map of deep neural networks G Valle-Pérez, CQ Camargo, AA Louis | | |