SAPPHIRE is a new preconditioned variance-reduced stochastic method with provable linear convergence for composite convex problems, achieving large speedups on regularized ERM.
Katyusha: The first direct acceleration of stochastic gradient methods.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
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SAPPHIRE: Preconditioned Stochastic Variance Reduction for Faster Large-Scale Statistical Learning
SAPPHIRE is a new preconditioned variance-reduced stochastic method with provable linear convergence for composite convex problems, achieving large speedups on regularized ERM.