Picture for Hugo Cui

Hugo Cui

A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities

Add code
Oct 24, 2024
Viaarxiv icon

High-dimensional learning of narrow neural networks

Add code
Sep 20, 2024
Viaarxiv icon

Asymptotics of Learning with Deep Structured (Random) Features

Add code
Feb 21, 2024
Viaarxiv icon

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

Add code
Feb 07, 2024
Viaarxiv icon

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

Add code
Feb 06, 2024
Viaarxiv icon

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

Add code
Oct 05, 2023
Viaarxiv icon

High-dimensional Asymptotics of Denoising Autoencoders

Add code
May 18, 2023
Viaarxiv icon

Deterministic equivalent and error universality of deep random features learning

Add code
Feb 01, 2023
Viaarxiv icon

Optimal Learning of Deep Random Networks of Extensive-width

Add code
Feb 01, 2023
Viaarxiv icon

Error Rates for Kernel Classification under Source and Capacity Conditions

Add code
Jan 29, 2022
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