Follow
Luca Pesce
Luca Pesce
PhD student, EPFL
Verified email at epfl.ch - Homepage
Title
Cited by
Cited by
Year
How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
Y Dandi, F Krzakala, B Loureiro, L Pesce, L Stephan
Journal of Machine Learning Research 25 (349), 1-65, 2024
392024
Are Gaussian data all you need? The extents and limits of universality in high-dimensional generalized linear estimation
L Pesce, F Krzakala, B Loureiro, L Stephan
International Conference on Machine Learning, 27680-27708, 2023
252023
The benefits of reusing batches for gradient descent in two-layer networks: Breaking the curse of information and leap exponents
Y Dandi, E Troiani, L Arnaboldi, L Pesce, L Zdeborová, F Krzakala
arXiv preprint arXiv:2402.03220, 2024
202024
Asymptotics of feature learning in two-layer networks after one gradient-step
H Cui, L Pesce, Y Dandi, F Krzakala, YM Lu, L Zdeborová, B Loureiro
arXiv preprint arXiv:2402.04980, 2024
152024
Repetita iuvant: Data repetition allows sgd to learn high-dimensional multi-index functions
L Arnaboldi, Y Dandi, F Krzakala, L Pesce, L Stephan
arXiv preprint arXiv:2405.15459, 2024
72024
Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs
L Arnaboldi, Y Dandi, F Krzakala, B Loureiro, L Pesce, L Stephan
arXiv preprint arXiv:2406.02157, 2024
22024
Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap
L Pesce, B Loureiro, F Krzakala, L Zdeborová
Advances in Neural Information Processing Systems 35, 27087-27099, 2022
22022
Theory and applications of the Sum-Of-Squares technique
F Bach, E Cornacchia, L Pesce, G Piccioli
Journal of Statistical Mechanics: Theory and Experiment 2024 (10), 104010, 2024
12024
A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities
Y Dandi, L Pesce, H Cui, F Krzakala, YM Lu, B Loureiro
arXiv preprint arXiv:2410.18938, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–9