Establishes a central limit theorem for averaged Adam with n^{-1/2} convergence rate to an attracting zero and covariance determined by the algorithm at the attractor.
Blow up phenomena for gradient descent optimization methods in the training of artificial neural networks.arXiv:2211.15641, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.PR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Central limit theorem for the averaged Adam optimizer
Establishes a central limit theorem for averaged Adam with n^{-1/2} convergence rate to an attracting zero and covariance determined by the algorithm at the attractor.