activity
20172026
most citedImplicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning

104 citations · 256 across the 9 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.LG2026

Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory

Hari K. Prakash, Charles H Martin

Training Neural Networks (NNs) without overfitting is difficult; detecting that overfitting is difficult as well. We present a novel Random Matrix Theory method that detects the on…