A Random Matrix Theory method identifies growing Correlation Traps in neural network weight spectra during an 'anti-grokking' overfitting phase, and applies the same diagnostic to some foundation LLMs.
Statistical mechanics approach to early stopping and weight decay.Physical Review E, 58(1):833–847
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
A Random Matrix Theory method identifies growing Correlation Traps in neural network weight spectra during an 'anti-grokking' overfitting phase, and applies the same diagnostic to some foundation LLMs.