collaborators

6 papers

cs.LG2026

Model Fusion via Retrofitting

Phoomraphee Luenam, Andreas Spanopoulos, Amit Sant +3

Model fusion seeks to combine independently trained neural networks into a single model without retraining, but is complicated by representational divergence arising from permutati…

cs.LG2025

Generalized Linear Mode Connectivity for Transformers

Alexander Theus, Alessandro Cabodi, Sotiris Anagnostidis +3

Understanding the geometry of neural network loss landscapes is a central question in deep learning, with implications for generalization and optimization. A striking phenomenon is…

cs.LG2025

Accelerating Neural Network Training Along Sharp and Flat Directions

Daniyar Zakarin, Sidak Pal Singh

Recent work has highlighted a surprising alignment between gradients and the top eigenspace of the Hessian -- termed the Dominant subspace -- during neural network training. Concur…

cs.LG2025

What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis

Weronika Ormaniec, Felix Dangel, Sidak Pal Singh

The Transformer architecture has inarguably revolutionized deep learning, overtaking classical architectures like multi-layer perceptrons (MLPs) and convolutional neural networks (…

cs.LG2025

Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks

Jim Zhao, Sidak Pal Singh, Aurelien Lucchi

The Gauss-Newton (GN) matrix plays an important role in machine learning, most evident in its use as a preconditioning matrix for a wide family of popular adaptive methods to speed…

cs.LG2025

Avoiding spurious sharpness minimization broadens applicability of SAM

Sidak Pal Singh, Hossein Mobahi, Atish Agarwala +1

Curvature regularization techniques like Sharpness Aware Minimization (SAM) have shown great promise in improving generalization on vision tasks. However, we find that SAM performs…