Goldt, Sebastian Dominik
Goldt, Sebastian Dominik
A distributional simplicity bias in the learning dynamics of transformers
2024-01-01 Rende, R; Gerace, F; Laio, A; Goldt, S
A simple linear algebra identity to optimize large-scale neural network quantum states
2024-01-01 Rende, Riccardo; Viteritti, Luciano Loris; Bardone, Lorenzo; Becca, Federico; Goldt, Sebastian
Align, then memorise: the dynamics of learning with feedback alignment
2021-01-01 Refinetti, M.; D'Ascoli, S.; Ohana, R.; Goldt, S.
Analysing the dynamics of online learning in over-parameterised two-layer neural networks
2019-01-01 Goldt, Sebastian; Advani, Madhu; Saxe, Andrew; Krzakala, Florent; Zdeborová, Lenka
Attacks on Online Learners: a Teacher-Student Analysis
2023-01-01 Margiotta, Riccardo G.; Goldt, Sebastian; Sanguinetti, Guido
Bayesian reconstruction of memories stored in neural networks from their connectivity
2023-01-01 Goldt, S.; Krzakala, F.; Zdeborova, L.; Brunel, N.
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
2021-01-01 Refinetti, M.; Goldt, S.; Krzakala, F.; Zdeborova, L.
Continual Learning in the Teacher-Student Setup: Impact of Task Similarity
2021-01-01 Lee, Sebastian; Goldt, Sebastian; Saxe, Andrew
Data-driven emergence of convolutional structure in neural networks
2022-01-01 Ingrosso, A.; Goldt, S.
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
2019-01-01 Goldt, Sebastian; Advani, Madhu; Saxe, Andrew; Krzakala, Florent; Zdeborová, Lenka
Learning curves of generic features maps for realistic datasets with a teacher-student model
2021-01-01 Loureiro, B.; Gerbelot, C.; Cui, H.; Goldt, S.; Krzakala, F.; Mezard, M.; Zdeborova, L.
Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks
2024-01-01 Székely, E; Bardone, L; Gerace, F; Goldt, S
Mapping of attention mechanisms to a generalized Potts model
2024-01-01 Rende, Riccardo; Gerace, Federica; Laio, Alessandro; Goldt, Sebastian
Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation
2022-01-01 Lee, S.; Mannelli, S. S.; Clopath, C.; Goldt, S.; Saxe, A.
Modeling the Influence of Data Structure on Learning in Neural Networks: The Hidden Manifold Model
2020-01-01 Goldt, S.; Mezard, M.; Krzakala, F.; Zdeborova, L.
Neural networks trained with SGD learn distributions of increasing complexity
2023-01-01 Refinetti, Maria; Ingrosso, Alessandro; Goldt, Sebastian
Perspectives on adaptive dynamical systems
2023-01-01 Sawicki, J.; Berner, R.; Loos, S. A. M.; Anvari, M.; Bader, R.; Barfuss, W.; Botta, N.; Brede, N.; Franovic, I.; Gauthier, D. J.; Goldt, S.; Hajizadeh, A.; Hovel, P.; Karin, O.; Lorenz-Spreen, P.; Miehl, C.; Molter, J.; Olmi, S.; Scholl, E.; Seif, A.; Tass, P. A.; Volpe, G.; Yanchuk, S.; Kurths, J.
Quantifying lottery tickets under label noise: accuracy, calibration, and complexity
2023-01-01 Arora, Viplove; Irto, Daniele; Goldt, Sebastian; Sanguinetti, Guido
Redundant representations help generalization in wide neural networks
2022-01-01 Doimo, D.; Glielmo, A.; Goldt, S.; Laio, A.
Representation mitosis in wide neural networks
2021-01-01 Doimo, Diego; Glielmo, Aldo; Goldt, Sebastian Dominik; Laio, Alessandro