Segui
Francesca Mignacco
Francesca Mignacco
Simons Junior Fellow, Princeton University & City University of New York
Email verificata su princeton.edu
Titolo
Citata da
Citata da
Anno
The role of regularization in classification of high-dimensional noisy gaussian mixture
F Mignacco, F Krzakala, Y Lu, P Urbani, L Zdeborova
International conference on machine learning, 6874-6883, 2020
992020
Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification
F Mignacco, F Krzakala, P Urbani, L Zdeborová
Advances in Neural Information Processing Systems 33, 2020
842020
The effective noise of stochastic gradient descent
F Mignacco, P Urbani
Journal of Statistical Mechanics: Theory and Experiment 2022 (8), 083405, 2022
422022
Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem
F Mignacco, P Urbani, L Zdeborová
Machine Learning: Science and Technology 2 (3), 035029, 2021
412021
Rigorous dynamical mean-field theory for stochastic gradient descent methods
C Gerbelot, E Troiani, F Mignacco, F Krzakala, L Zdeborova
SIAM Journal on Mathematics of Data Science 6 (2), 400-427, 2024
322024
Learning curves for the multi-class teacher–student perceptron
E Cornacchia, F Mignacco, R Veiga, C Gerbelot, B Loureiro, L Zdeborová
Machine Learning: Science and Technology 4 (1), 015019, 2023
192023
Forward learning with top-down feedback: Empirical and analytical characterization
RF Srinivasan, F Mignacco, M Sorbaro, M Refinetti, A Cooper, G Kreiman, ...
The Twelfth International Conference on Learning Representations, 2023
152023
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers
L Tiberi, F Mignacco, K Irie, H Sompolinsky
arXiv preprint arXiv:2405.15926, 2024
52024
High-dimensional non-convex landscapes and gradient descent dynamics
T Bonnaire, D Ghio, K Krishnamurthy, F Mignacco, A Yamamura, G Biroli
Journal of Statistical Mechanics: Theory and Experiment 2024 (10), 104004, 2024
22024
Optimal protocols for continual learning via statistical physics and control theory
F Mori, SS Mannelli, F Mignacco
arXiv preprint arXiv:2409.18061, 2024
12024
Nonlinear classification of neural manifolds with contextual information
F Mignacco, CN Chou, SY Chung
arXiv preprint arXiv:2405.06851, 2024
12024
Learning from setbacks: the impact of adversarial initialization on generalization performance
K Ravichandran, Y Dandi, S Karp, F Mignacco
NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning, 0
1
Nonlinear classification of neural manifolds with context information: geometrical properties and storage capacity
F Mignacco, CN Chou, SY Chung
Bulletin of the American Physical Society, 2024
2024
Minimax entropy principle and dimensionality reduction in neural data
L Di Carlo, F Mignacco, W Bialek
Bulletin of the American Physical Society, 2024
2024
Statistical physics insights on the dynamics and generalisation of artificial neural networks
F Mignacco
Université Paris-Saclay, 2022
2022
Statistical physics insights on learning in high dimensions
F Mignacco
APS March Meeting Abstracts 2022, B42. 001, 2022
2022
Understanding multi-pass stochastic gradient descent via dynamical mean-field theory
F Mignacco
APS March Meeting Abstracts 2022, K02. 009, 2022
2022
Il sistema al momento non puň eseguire l'operazione. Riprova piů tardi.
Articoli 1–17