An inexact proximal-point penalty algorithm finds ε-stationary points of non-convex constrained problems in O~(ε^{-5/2}) steps with convex constraints and O~(ε^{-3}) to O~(ε^{-4}) steps with non-convex constraints.
Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this paper, we introduce a stochastic projected subgradient method for weakly convex (i.e., uniformly prox-regular) nonsmooth, nonconvex functions---a wide class of functions which includes the additive and convex composite classes. At a high-level, the method is an inexact proximal point iteration in which the strongly convex proximal subproblems are quickly solved with a specialized stochastic projected subgradient method. The primary contribution of this paper is a simple proof that the proposed algorithm converges at the same rate as the stochastic gradient method for smooth nonconvex problems. This result appears to be the first convergence rate analysis of a stochastic (or even deterministic) subgradient method for the class of weakly convex functions.
fields
math.OC 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Inexact Proximal-Point Penalty Methods for Constrained Non-Convex Optimization
An inexact proximal-point penalty algorithm finds ε-stationary points of non-convex constrained problems in O~(ε^{-5/2}) steps with convex constraints and O~(ε^{-3}) to O~(ε^{-4}) steps with non-convex constraints.