Double trouble in double descent: Bias and variance (s) in the lazy regime S d’Ascoli, M Refinetti, G Biroli, F Krzakala International Conference on Machine Learning, 2280-2290, 2020 | 159 | 2020 |
Classifying high-dimensional gaussian mixtures: Where kernel methods fail and neural networks succeed M Refinetti, S Goldt, F Krzakala, L Zdeborová International Conference on Machine Learning, 8936-8947, 2021 | 78 | 2021 |
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 | 45 | 2021 |
Epidemic mitigation by statistical inference from contact tracing data A Baker, I Biazzo, A Braunstein, G Catania, L Dall’Asta, A Ingrosso, ... Proceedings of the National Academy of Sciences 118 (32), e2106548118, 2021 | 30 | 2021 |
Fluctuations, bias, variance & ensemble of learners: Exact asymptotics for convex losses in high-dimension B Loureiro, C Gerbelot, M Refinetti, G Sicuro, F Krzakala International Conference on Machine Learning, 14283-14314, 2022 | 27 | 2022 |
Neural networks trained with SGD learn distributions of increasing complexity M Refinetti, A Ingrosso, S Goldt International Conference on Machine Learning, 28843-28863, 2023 | 22 | 2023 |
Bootstrapping traceless symmetric scalars M Reehorst, M Refinetti, A Vichi SciPost Physics 14 (4), 068, 2023 | 15 | 2023 |
The dynamics of representation learning in shallow, non-linear autoencoders M Refinetti, S Goldt International Conference on Machine Learning, 18499-18519, 2022 | 12 | 2022 |
Forward learning with top-down feedback: Empirical and analytical characterization RF Srinivasan, F Mignacco, M Sorbaro, M Refinetti, A Cooper, G Kreiman, ... arXiv preprint arXiv:2302.05440, 2023 | 10 | 2023 |
Optimal learning rate schedules in high-dimensional non-convex optimization problems S d'Ascoli, M Refinetti, G Biroli arXiv preprint arXiv:2202.04509, 2022 | 4 | 2022 |
Fluctuations, bias, variance and ensemble of learners: exact asymptotics for convex losses in high-dimension B Loureiro, C Gerbelot, M Refinetti, G Sicuro, F Krzakala Journal of Statistical Mechanics: Theory and Experiment 2023 (11), 114001, 2023 | 1 | 2023 |
The dynamics of representation learning in shallow, non-linear autoencoders M Refinetti, S Goldt Journal of Statistical Mechanics: Theory and Experiment 2023 (11), 114010, 2023 | | 2023 |
The Role of Architecture, Data Structure and Algorithm in Machine Learning: a Statistical Physics Approach M Refinetti Sorbonne Université, 2022 | | 2022 |