Gradient-based SVD diagnostic uncovers hidden SED-LCH coupling in single and multitask settings and shows rank-3 subspace constraints speed up grokking by 2.3x.
Zico Kolter, and Ameet Talwalkar.Gradient descent on neural networks typically occurs at the edge of stability.In International Conference on Learning Representations (ICLR)
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
-
Gradient-Direction Sensitivity Reveals Linear-Centroid Coupling Hidden by Optimizer Trajectories
Gradient-based SVD diagnostic uncovers hidden SED-LCH coupling in single and multitask settings and shows rank-3 subspace constraints speed up grokking by 2.3x.