arXiv Machine Learning By Marcelina Marjankowska, Valerio Modugno, Paolo Barucca

Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization

Read the original on arXiv Machine Learning →

arXiv:2606. 30226v1 Announce Type: new Abstract: Hessian spectral properties are a standard tool in analysing neural-network training, with eigenvalues linked to sharpness, generalization, and optimization dynamics.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers
Jul 15

How the Hessian-Spectrum of Neural Networks Depends on Data

The Hessian matrix is an important quantity of interest when it comes to studying the loss landscape and optimization dynamics in deep learning, as well as designing measures of generalization, second-order learning algorithms, etc. Prior works have focused on empirical results or pursued a theoretical treatment under overly simplified settings.