Proposes an incremental variance-reduced stochastic gradient method for minimizing smooth nonconvex composite functions that achieves optimal first-order complexity rates.
Summing this up and apply the random selection rule of ¯ x gives E[Φ( ¯x) − Φ∗] ≤ 1 2µητT E[Φ( x1 0 ) − Φ∗ + 2µ∥x1 0 − x∗∥2] + 9σ2 0 4µBt ≤ 5 2µητT E[Φ( x1 0 ) − Φ∗] + 9σ2 0 4µBt
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Stochastic Composite Gradient Method with Incremental Variance Reduction
Proposes an incremental variance-reduced stochastic gradient method for minimizing smooth nonconvex composite functions that achieves optimal first-order complexity rates.