activity
20182026
most citedCockpit: A Practical Debugging Tool for the Training of Deep Neural Networks

3 citations · 11 across the 23 of their papers we have counts for

collaborators
Showing 2025Show all

9 papers · 1 filter

cs.LG2025

Sketching Low-Rank Plus Diagonal Matrices

Andres Fernandez, Felix Dangel, Philipp Hennig +1

Many relevant machine learning and scientific computing tasks involve high-dimensional linear operators accessible only via costly matrix-vector products. In this context, recent a…

stat.ML2025

Understanding and Improving Shampoo and SOAP via Kullback-Leibler Minimization

Wu Lin, Scott C. Lowe, Felix Dangel +3

Shampoo and its efficient variant, SOAP, employ structured second-moment estimations and have shown strong performance for training neural networks (NNs). In practice, however, Sha…

cs.LG2025

Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator

YuXin Li, Felix Dangel, Derek Tam +1

The diagonal of a model's Fisher Information Matrix (the "Fisher diagonal") has frequently been used as a way to measure parameter sensitivity. Typically, the Fisher diagonal is es…

cs.LG2025

Kronecker-factored Approximate Curvature (KFAC) From Scratch

Felix Dangel, Bálint Mucsányi, Tobias Weber +1

Kronecker-factored approximate curvature (KFAC) is arguably one of the most prominent curvature approximations in deep learning. Its applications range from optimization to Bayesia…

cs.LG2025

Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It

Marvin F. da Silva, Felix Dangel, Sageev Oore

The concept of sharpness has been successfully applied to traditional architectures like MLPs and CNNs to predict their generalization. For transformers, however, recent work repor…

cs.LG2025

Collapsing Taylor Mode Automatic Differentiation

Felix Dangel, Tim Siebert, Marius Zeinhofer +1

Computing partial differential equation (PDE) operators via nested backpropagation is expensive, yet popular, and severely restricts their utility for scientific machine learning.…