Stefano SARAO MANNELLI
Stefano SARAO MANNELLI
Gatsby Computational Neuroscience Unit & Sainsbury Wellcome Centre | University College London
Adresse e-mail validée de ucl.ac.uk - Page d'accueil
Titre
Citée par
Citée par
Année
Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models
S Sarao Mannelli, F Krzakala, P Urbani, L Zdeborova
International Conference on Machine Learning, 4333-4342, 2019
272019
Marvels and pitfalls of the langevin algorithm in noisy high-dimensional inference
S Sarao Mannelli, G Biroli, C Cammarota, F Krzakala, P Urbani, ...
Physical Review X 10 (1), 011057, 2020
242020
Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models
S Sarao Mannelli, G Biroli, C Cammarota, F Krzakala, L Zdeborová
Advances in Neural Information Processing Systems, 8676-8686, 2019
202019
Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions
S Sarao Mannelli, E Vanden-Eijnden, L Zdeborová
Advances in Neural Information Processing Systems 33, 13445--13455, 2020
12*2020
Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval
S Sarao Mannelli, G Biroli, C Cammarota, F Krzakala, P Urbani, ...
Advances in Neural Information Processing Systems 33, 3265--3274, 2020
7*2020
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), 2021
22021
Thresholds of descending algorithms in inference problems
S Sarao Mannelli, L Zdeborova
Journal of Statistical Mechanics: Theory and Experiment 2020 (3), 034004, 2020
22020
Probing transfer learning with a model of synthetic correlated datasets
F Gerace, L Saglietti, S Sarao Mannelli, A Saxe, L Zdeborová
arXiv preprint arXiv:2106.05418, 2021
12021
An Analytical Theory of Curriculum Learning in Teacher-Student Networks
L Saglietti, S Sarao Mannelli, A Saxe
arXiv preprint arXiv:2106.08068, 2021
2021
Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems
S Sarao Mannelli, P Urbani
Advances in Neural Information Processing Systems, 2021, 0
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–10