متابعة
Luca Saglietti
Luca Saglietti
Bocconi University - Computing Sciences
بريد إلكتروني تم التحقق منه على unibocconi.it - الصفحة الرئيسية
عنوان
عدد مرات الاقتباسات
عدد مرات الاقتباسات
السنة
Unreasonable effectiveness of learning neural networks: From accessible states and robust ensembles to basic algorithmic schemes‏
C Baldassi, C Borgs, JT Chayes, A Ingrosso, C Lucibello, L Saglietti, ...‏
Proceedings of the National Academy of Sciences 113 (48), E7655-E7662, 2016‏
2072016
Subdominant dense clusters allow for simple learning and high computational performance in neural networks with discrete synapses‏
C Baldassi, A Ingrosso, C Lucibello, L Saglietti, R Zecchina‏
Physical review letters 115 (12), 128101, 2015‏
1682015
Gaussian process prior variational autoencoders‏
FP Casale, A Dalca, L Saglietti, J Listgarten, N Fusi‏
Advances in neural information processing systems 31, 2018‏
1562018
Local entropy as a measure for sampling solutions in constraint satisfaction problems‏
C Baldassi, A Ingrosso, C Lucibello, L Saglietti, R Zecchina‏
Journal of Statistical Mechanics: Theory and Experiment 2016 (2), 023301, 2016‏
662016
Learning may need only a few bits of synaptic precision‏
C Baldassi, F Gerace, C Lucibello, L Saglietti, R Zecchina‏
Physical Review E 93 (5), 052313, 2016‏
382016
Probing transfer learning with a model of synthetic correlated datasets‏
F Gerace, L Saglietti, SS Mannelli, A Saxe, L Zdeborová‏
Machine Learning: Science and Technology 3 (1), 015030, 2022‏
362022
An analytical theory of curriculum learning in teacher-student networks‏
L Saglietti, S Mannelli, A Saxe‏
Advances in Neural Information Processing Systems 35, 21113-21127, 2022‏
292022
Role of synaptic stochasticity in training low-precision neural networks‏
C Baldassi, F Gerace, HJ Kappen, C Lucibello, L Saglietti, E Tartaglione, ...‏
Physical review letters 120 (26), 268103, 2018‏
272018
Solvable model for inheriting the regularization through knowledge distillation‏
L Saglietti, L Zdeborová‏
Mathematical and Scientific Machine Learning, 809-846, 2022‏
252022
Star-shaped space of solutions of the spherical negative perceptron‏
BL Annesi, C Lauditi, C Lucibello, EM Malatesta, G Perugini, F Pittorino, ...‏
Physical Review Letters 131 (22), 227301, 2023‏
172023
Generalized approximate survey propagation for high-dimensional estimation‏
C Lucibello, L Saglietti, Y Lu‏
International Conference on Machine Learning, 4173-4182, 2019‏
132019
Large deviations in the perceptron model and consequences for active learning‏
H Cui, L Saglietti, L Zdeborová‏
Machine Learning: Science and Technology 2 (4), 045001, 2021‏
92021
From statistical inference to a differential learning rule for stochastic neural networks‏
L Saglietti, F Gerace, A Ingrosso, C Baldassi, R Zecchina‏
Interface Focus 8 (6), 20180033, 2018‏
72018
From inverse problems to learning: a statistical mechanics approach‏
C Baldassi, F Gerace, L Saglietti, R Zecchina‏
Journal of Physics: Conference Series 955 (1), 012001, 2018‏
72018
How transformers learn structured data: insights from hierarchical filtering‏
J Garnier-Brun, M Mézard, E Moscato, L Saglietti‏
arXiv preprint arXiv:2408.15138, 2024‏
42024
Compressed sensing with ℓ0-norm: statistical physics analysis & algorithms for signal recovery‏
D Barbier, C Lucibello, L Saglietti, F Krzakala, L Zdeborová‏
2023 IEEE Information Theory Workshop (ITW), 323-328, 2023‏
42023
Unfair geometries: exactly solvable data model with fairness implications‏
SS Mannelli, F Gerace, N Rostamzadeh, L Saglietti‏
arXiv preprint arXiv:2205.15935, 2022‏
42022
Large deviations for the perceptron model and consequences for active learning‏
H Cui, L Saglietti, L Zdeborova‏
Mathematical and Scientific Machine Learning, 390-430, 2020‏
42020
Bias-inducing geometries: exactly solvable data model with fairness implications‏
SS Mannelli, F Gerace, N Rostamzadeh, L Saglietti‏
ICML 2024 Workshop on Geometry-grounded Representation Learning and …, 2024‏
22024
Optimal transfer protocol by incremental layer defrosting‏
F Gerace, D Doimo, SS Mannelli, L Saglietti, A Laio‏
arXiv preprint arXiv:2303.01429, 2023‏
12023
يتعذر على النظام إجراء العملية في الوقت الحالي. عاود المحاولة لاحقًا.
مقالات 1–20