Alert button
Picture for Hugo Cui

Hugo Cui

Alert button

Asymptotics of Learning with Deep Structured (Random) Features

Feb 21, 2024
Dominik Schröder, Daniil Dmitriev, Hugo Cui, Bruno Loureiro

Viaarxiv icon

Asymptotics of feature learning in two-layer networks after one gradient-step

Feb 07, 2024
Hugo Cui, Luca Pesce, Yatin Dandi, Florent Krzakala, Yue M. Lu, Lenka Zdeborová, Bruno Loureiro

Viaarxiv icon

A phase transition between positional and semantic learning in a solvable model of dot-product attention

Feb 06, 2024
Hugo Cui, Freya Behrens, Florent Krzakala, Lenka Zdeborová

Viaarxiv icon

Analysis of learning a flow-based generative model from limited sample complexity

Oct 05, 2023
Hugo Cui, Florent Krzakala, Eric Vanden-Eijnden, Lenka Zdeborová

Viaarxiv icon

High-dimensional Asymptotics of Denoising Autoencoders

May 18, 2023
Hugo Cui, Lenka Zdeborová

Figure 1 for High-dimensional Asymptotics of Denoising Autoencoders
Figure 2 for High-dimensional Asymptotics of Denoising Autoencoders
Figure 3 for High-dimensional Asymptotics of Denoising Autoencoders
Figure 4 for High-dimensional Asymptotics of Denoising Autoencoders
Viaarxiv icon

Deterministic equivalent and error universality of deep random features learning

Feb 01, 2023
Dominik Schröder, Hugo Cui, Daniil Dmitriev, Bruno Loureiro

Figure 1 for Deterministic equivalent and error universality of deep random features learning
Figure 2 for Deterministic equivalent and error universality of deep random features learning
Figure 3 for Deterministic equivalent and error universality of deep random features learning
Figure 4 for Deterministic equivalent and error universality of deep random features learning
Viaarxiv icon

Optimal Learning of Deep Random Networks of Extensive-width

Feb 01, 2023
Hugo Cui, Florent Krzakala, Lenka Zdeborová

Figure 1 for Optimal Learning of Deep Random Networks of Extensive-width
Figure 2 for Optimal Learning of Deep Random Networks of Extensive-width
Figure 3 for Optimal Learning of Deep Random Networks of Extensive-width
Figure 4 for Optimal Learning of Deep Random Networks of Extensive-width
Viaarxiv icon

Error Rates for Kernel Classification under Source and Capacity Conditions

Jan 29, 2022
Hugo Cui, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová

Figure 1 for Error Rates for Kernel Classification under Source and Capacity Conditions
Figure 2 for Error Rates for Kernel Classification under Source and Capacity Conditions
Figure 3 for Error Rates for Kernel Classification under Source and Capacity Conditions
Figure 4 for Error Rates for Kernel Classification under Source and Capacity Conditions
Viaarxiv icon

Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime

May 31, 2021
Hugo Cui, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová

Figure 1 for Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
Figure 2 for Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
Figure 3 for Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
Figure 4 for Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
Viaarxiv icon

Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model

Feb 16, 2021
Bruno Loureiro, Cédric Gerbelot, Hugo Cui, Sebastian Goldt, Florent Krzakala, Marc Mézard, Lenka Zdeborová

Figure 1 for Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model
Figure 2 for Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model
Figure 3 for Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model
Figure 4 for Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model
Viaarxiv icon