Sledovat
Luca Pesce
Luca Pesce
PhD student, EPFL
E-mailová adresa ověřena na: epfl.ch
Název
Citace
Citace
Rok
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
132023
Learning two-layer neural networks, one (giant) step at a time
Y Dandi, F Krzakala, B Loureiro, L Pesce, L Stephan
arXiv preprint arXiv:2305.18270, 2023
122023
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
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
12022
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
2024
Theory and applications of the Sum-Of-Squares technique
F Bach, E Cornacchia, L Pesce, G Piccioli
arXiv preprint arXiv:2306.16255, 2023
2023
Systém momentálně nemůže danou operaci provést. Zkuste to znovu později.
Články 1–6