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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SGD on neural network weights induces a BBP phase transition that detaches signal eigenvalues from the random bulk, yielding an analytically solvable phase diagram for trainability in a linear teacher-student model.
citing papers explorer
-
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.
-
Spectral phase transitions and trainability in neural network learning dynamics
SGD on neural network weights induces a BBP phase transition that detaches signal eigenvalues from the random bulk, yielding an analytically solvable phase diagram for trainability in a linear teacher-student model.