Worker-average gaps in Local SGD serve as a Hessian-free estimator of the dominant sharp subspace by capturing gradient alignment with high-curvature directions.
Low dimensional trajectory hypothesis is true: Dnns can be trained in tiny subspaces.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3):3411–3420, 2023
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
-
Worker Disagreement Reveals Sharp Directions in Local SGD
Worker-average gaps in Local SGD serve as a Hessian-free estimator of the dominant sharp subspace by capturing gradient alignment with high-curvature directions.