Hugo Cui
Hugo Cui
PhD student, EPFL
Verified email at
Cited by
Cited by
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
Generalization error rates in kernel regression: The crossover from the noiseless to noisy regime
H Cui, B Loureiro, F Krzakala, L Zdeborová
Advances in Neural Information Processing Systems 34, 10131-10143, 2021
Deterministic equivalent and error universality of deep random features learning
D Schröder, H Cui, D Dmitriev, B Loureiro
International Conference on Machine Learning, 30285-30320, 2023
Bayes-optimal learning of deep random networks of extensive-width
H Cui, F Krzakala, L Zdeborová
International Conference on Machine Learning 40, 6468-6521, 2023
Error scaling laws for kernel classification under source and capacity conditions
H Cui, B Loureiro, F Krzakala, L Zdeborová
Machine Learning: Science and Technology 4 (3), 035033, 2023
High-dimensional asymptotics of denoising autoencoders
H Cui, L Zdeborová
Advances in Neural Information Processing Systems 36, 2024
Analysis of learning a flow-based generative model from limited sample complexity
H Cui, F Krzakala, E Vanden-Eijnden, L Zdeborová
arXiv preprint arXiv:2310.03575, 2023
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
Asymptotics of Learning with Deep Structured (Random) Features
D Schröder, D Dmitriev, H Cui, B Loureiro
arXiv preprint arXiv:2402.13999, 2024
Asymptotics of feature learning in two-layer networks after one gradient-step
H Cui, L Pesce, Y Dandi, F Krzakala, YM Lu, L Zdeborová, B Loureiro
arXiv preprint arXiv:2402.04980, 2024
A phase transition between positional and semantic learning in a solvable model of dot-product attention
H Cui, F Behrens, F Krzakala, L Zdeborová
arXiv preprint arXiv:2402.03902, 2024
Large deviations of semisupervised learning in the stochastic block model
H Cui, L Saglietti, L Zdeborová
Physical Review E 105 (3), 034108, 2022
The system can't perform the operation now. Try again later.
Articles 1–12