Negative eigenvalues of the Hessian in deep neural networks
classification
💻 cs.LG
math.OCstat.ML
keywords
deepnetworkseigenvalueshessianlossnegativeactiveappropriately
read the original abstract
The loss function of deep networks is known to be non-convex but the precise nature of this nonconvexity is still an active area of research. In this work, we study the loss landscape of deep networks through the eigendecompositions of their Hessian matrix. In particular, we examine how important the negative eigenvalues are and the benefits one can observe in handling them appropriately.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization
Hessian eigenvector displacement and inverse participation ratio metrics show SGD stabilizing leading curvature directions while Adam causes more reorganization and parameter localization in MLP training.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.