In an anisotropic random-matrix model of gradient flow, the teacher signal produces a transient BBP transition where the outlier eigenvalue emerges only in an intermediate time window before overfitting.
The role of the time-dependent hessian in high-dimensional optimization.Journal of Statistical Mechanics: Theory and Experiment, 2025(8):083401
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario
In an anisotropic random-matrix model of gradient flow, the teacher signal produces a transient BBP transition where the outlier eigenvalue emerges only in an intermediate time window before overfitting.