Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning L Seydoux, R Balestriero, P Poli, M Hoop, M Campillo, R Baraniuk Nature communications 11 (1), 3972, 2020 | 160 | 2020 |
A spline theory of deep learning R Balestriero, R Baraniuk International Conference on Machine Learning, 374-383, 2018 | 128 | 2018 |
Learning in high dimension always amounts to extrapolation R Balestriero, J Pesenti, Y LeCun arXiv preprint arXiv:2110.09485, 2021 | 119 | 2021 |
Contrastive and non-contrastive self-supervised learning recover global and local spectral embedding methods R Balestriero, Y LeCun Advances in Neural Information Processing Systems 35, 26671-26685, 2022 | 114 | 2022 |
Mad max: Affine spline insights into deep learning R Balestriero, RG Baraniuk Proceedings of the IEEE, 1-24, 2020 | 97 | 2020 |
The effects of regularization and data augmentation are class dependent R Balestriero, L Bottou, Y LeCun Advances in Neural Information Processing Systems 35, 37878-37891, 2022 | 81 | 2022 |
The recurrent neural tangent kernel S Alemohammad, Z Wang, R Balestriero, R Baraniuk International Conference on Learning Representations, 2020 | 77 | 2020 |
The geometry of deep networks: Power diagram subdivision R Balestriero, R Cosentino, B Aazhang, R Baraniuk Advances in Neural Information Processing Systems 32, 15832--15841, 2019 | 56 | 2019 |
Neural decision trees R Balestriero arXiv preprint arXiv:1702.07360, 2017 | 55 | 2017 |
Avi Schwarzschild, Andrew Gordon Wilson, Jonas Geiping, Quentin Garrido, Pierre Fernandez, Amir Bar, Hamed Pirsiavash, Yann LeCun, and Micah Goldblum R Balestriero, M Ibrahim, V Sobal, A Morcos, S Shekhar, T Goldstein, ... A cookbook of self-supervised learning 2, 2023 | 51 | 2023 |
Rankme: Assessing the downstream performance of pretrained self-supervised representations by their rank Q Garrido, R Balestriero, L Najman, Y Lecun International conference on machine learning, 10929-10974, 2023 | 49 | 2023 |
High fidelity visualization of what your self-supervised representation knows about F Bordes, R Balestriero, P Vincent arXiv preprint arXiv:2112.09164, 2021 | 45 | 2021 |
Spline filters for end-to-end deep learning R Balestriero, R Cosentino, H Glotin, R Baraniuk International conference on machine learning, 364-373, 2018 | 35 | 2018 |
Guillotine regularization: Why removing layers is needed to improve generalization in self-supervised learning F Bordes, R Balestriero, Q Garrido, A Bardes, P Vincent arXiv preprint arXiv:2206.13378, 2022 | 33* | 2022 |
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values A Imtiaz Humayun, R Balestriero, R Baraniuk arXiv e-prints, arXiv: 2203.01993, 2022 | 33* | 2022 |
Imagenet-x: Understanding model mistakes with factor of variation annotations BY Idrissi, D Bouchacourt, R Balestriero, I Evtimov, C Hazirbas, N Ballas, ... arXiv preprint arXiv:2211.01866, 2022 | 32 | 2022 |
The hidden uniform cluster prior in self-supervised learning M Assran, R Balestriero, Q Duval, F Bordes, I Misra, P Bojanowski, ... arXiv preprint arXiv:2210.07277, 2022 | 32 | 2022 |
A data-augmentation is worth a thousand samples: Analytical moments and sampling-free training R Balestriero, I Misra, Y LeCun Advances in Neural Information Processing Systems 35, 19631-19644, 2022 | 27* | 2022 |
MaGNET: Uniform sampling from deep generative network manifolds without retraining AI Humayun, R Balestriero, R Baraniuk arXiv preprint arXiv:2110.08009, 2021 | 27 | 2021 |
Implicit rugosity regularization via data augmentation D LeJeune, R Balestriero, H Javadi, RG Baraniuk arXiv preprint arXiv:1905.11639, 2019 | 23* | 2019 |