Large loss spikes in SGD are polynomially likely and serve as the dominant mechanism for escaping sharp minima toward flatter solutions in the NTK regime.
Towards explaining the regularization effect of initial large learning rate in training neural networks.Advances in neural information processing systems, 32, 2019
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
-
Large Spikes in Stochastic Gradient Descent: A Large-Deviations View
Large loss spikes in SGD are polynomially likely and serve as the dominant mechanism for escaping sharp minima toward flatter solutions in the NTK regime.