Sebastian Goldt
Cytowane przez
Cytowane przez
Modelling the influence of data structure on learning in neural networks: the hidden manifold model
S Goldt, M Mézard, F Krzakala, L Zdeborová
Physical Review X 10 (4), 041044, 2019
Stochastic thermodynamics of resetting
J Fuchs*, S Goldt*, U Seifert
EPL (Europhysics Letters) 113 (6), 60009, 2016
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
S Goldt, MS Advani, AM Saxe, F Krzakala, L Zdeborová
Advances in Neural Information Processing Systems 32, 6979--6989, 2019
Stochastic thermodynamics of learning
S Goldt, U Seifert
Physical review letters 118 (1), 010601, 2017
The Gaussian equivalence of generative models for learning with shallow neural networks
S Goldt, B Loureiro, G Reeves, F Krzakala, M Mézard, L Zdeborová
Mathematical and Scientific Machine Learning, 426-471, 2022
Learning curves of generic features maps for realistic datasets with a teacher-student model
B Loureiro, C Gerbelot, H Cui, S Goldt, F Krzakala, M Mezard, ...
Advances in Neural Information Processing Systems 34, 18137-18151, 2021
Zinc finger proteins and the 3D organization of chromosomes
CJ Feinauer, A Hofmann, S Goldt, L Liu, G Mate, DW Heermann
Advances in protein chemistry and structural biology 90, 67-117, 2013
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
M Refinetti, S Goldt, F Krzakala, L Zdeborová
International Conference on Machine Learning, 8936-8947, 2021
Align, then memorise: the dynamics of learning with feedback alignment
M Refinetti, S d’Ascoli, R Ohana, S Goldt
International Conference on Machine Learning, 8925-8935, 2021
Thermodynamic efficiency of learning a rule in neural networks
S Goldt, U Seifert
New Journal of Physics 19 (11), 113001, 2017
Continual learning in the teacher-student setup: Impact of task similarity
S Lee, S Goldt, A Saxe
International Conference on Machine Learning, 6109-6119, 2021
Generalisation dynamics of online learning in over-parameterised neural networks
S Goldt, MS Advani, AM Saxe, F Krzakala, L Zdeborová
ICML 2019 Workshop on Theoretical Physics for Deep Learning, 2019
Role of the potential landscape on the single-file diffusion through channels
SD Goldt, EM Terentjev
The Journal of Chemical Physics 141 (22), 224901, 2014
Data-driven emergence of convolutional structure in neural networks
A Ingrosso, S Goldt
arXiv preprint arXiv:2202.00565, 2022
The dynamics of representation learning in shallow, non-linear autoencoders
M Refinetti, S Goldt
arXiv preprint arXiv:2201.02115, 2022
Bayesian reconstruction of memories stored in neural networks from their connectivity
S Goldt, F Krzakala, L Zdeborová, N Brunel
arXiv preprint arXiv:2105.07416, 2021
The impact of memory on learning sequence-to-sequence tasks
A Seif, SAM Loos, G Tucci, É Roldán, S Goldt
arXiv preprint arXiv:2205.14683, 2022
Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation
S Lee, SS Mannelli, C Clopath, S Goldt, A Saxe
arXiv preprint arXiv:2205.09029, 2022
Representation mitosis in wide neural networks
D Doimo, A Glielmo, S Goldt, A Laio
arXiv preprint arXiv:2106.03485, 2021
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–19