collaborators

15 papers

stat.ML2026

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.LG2026

Exploiting weight-space symmetries for approximating curvature

Artem Artemev, Rui Xia, Benjamin M. Boyd +4

Many machine learning techniques rely on approximating a loss function's curvature, but this is notoriously hard to do at the scale of modern deep networks. Surprisingly, no previo…

cs.LG2026

Reparametrizing Shampoo and SOAP for Subspace Basis Updates and BFloat16 Storage

Alan Milligan, Zikun Xu, Simon Lacoste-Julien +2

Shampoo-based methods, such as KL-Shampoo and SOAP, have demonstrated strong performance in training neural networks and rely on QR decomposition. Because existing QR implementatio…

cs.AI2026

Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature

Angelo Porrello, Pietro Buzzega, Felix Dangel +4

Task Arithmetic yields a modular, scalable way to adapt foundation models. Combining multiple task vectors, however, can lead to cross-task interference, causing representation dri…

cs.LG2026

Generalizing the Geometry of Model Merging Through Frechet Averages

Marvin F. da Silva, Mohammed Adnan, Felix Dangel +1

Model merging aims to combine multiple models into one without additional training. Naïve parameter-space averaging can be fragile under architectural symmetries, as their geometr…

cs.LG2026

Efficient Bilevel Optimization with KFAC-Based Hypergradients

Disen Liao, Felix Dangel, Yaoliang Yu

Bilevel optimization (BO) is widely applicable to many machine learning problems. Scaling BO, however, requires repeatedly computing hypergradients, which involves solving inverse…