Classical momentum acceleration in mini-batch SGD for quadratics is proportional to batch size up to saturation, enabling perfect parallelization under minimal noise assumptions.
Katyusha: The first direct acceleration of stochastic gradient meth- ods.Journal of Machine Learning Research, 18(221):1–51, 2018
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
-
Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration
Classical momentum acceleration in mini-batch SGD for quadratics is proportional to batch size up to saturation, enabling perfect parallelization under minimal noise assumptions.