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.
Raydan, The Barzilai and Borwein gradient method for the large scale unconstrained mini- mization problem, SIAM Journal on Optimization, 7(1) (1997), 26-33
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.