An adaptive joint scheduler that adjusts SGD batch size and learning rate from observed full-gradient-norm decay reportedly reaches solutions faster than existing schedulers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive Batch Size and Learning Rate Scheduler for Stochastic Gradient Descent Based on Minimization of Stochastic First-order Oracle Complexity
An adaptive joint scheduler that adjusts SGD batch size and learning rate from observed full-gradient-norm decay reportedly reaches solutions faster than existing schedulers.