Picture for Bruno Loureiro

Bruno Loureiro

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

Add code
Oct 24, 2024
Figure 1 for A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities
Figure 2 for A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities
Viaarxiv icon

On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds

Add code
Oct 21, 2024
Viaarxiv icon

A theoretical perspective on mode collapse in variational inference

Add code
Oct 17, 2024
Figure 1 for A theoretical perspective on mode collapse in variational inference
Figure 2 for A theoretical perspective on mode collapse in variational inference
Figure 3 for A theoretical perspective on mode collapse in variational inference
Figure 4 for A theoretical perspective on mode collapse in variational inference
Viaarxiv icon

Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs

Add code
Jun 04, 2024
Viaarxiv icon

Fundamental limits of weak learnability in high-dimensional multi-index models

Add code
May 24, 2024
Viaarxiv icon

Dimension-free deterministic equivalents for random feature regression

Add code
May 24, 2024
Viaarxiv icon

Asymptotics of Learning with Deep Structured (Random) Features

Add code
Feb 21, 2024
Viaarxiv icon

Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression

Add code
Feb 21, 2024
Viaarxiv icon

A High Dimensional Model for Adversarial Training: Geometry and Trade-Offs

Add code
Feb 08, 2024
Viaarxiv icon

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

Add code
Feb 07, 2024
Viaarxiv icon