A proximal stochastic gradient method with variance reduction and adaptive steps is shown to converge strongly at rate O(sqrt(1/k)) for convex composite problems when the smooth term is Lipschitz continuous.
Xiao, Dual averaging method for regularized stochastic learning and online optimization, The Journal of Machine Learning Research, 11 (2010), 2543-2596
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Proximal Stochastic Gradient Method with Adaptive Step Size and Variance Reduction for Convex Composite Optimization
A proximal stochastic gradient method with variance reduction and adaptive steps is shown to converge strongly at rate O(sqrt(1/k)) for convex composite problems when the smooth term is Lipschitz continuous.