REVIEW 4 cited by
Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 4 Pith papers
-
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.
-
Stochastic First-order Methods for Convex and Nonconvex Functional Constrained Optimization
ConEx, a single-loop primal-dual method with constraint extrapolation, achieves best-known convergence rates for convex functional constrained problems, and a proximal point method achieves O(1/ε) complexity to approx...
-
Quadratically Regularized Subgradient Methods for Weakly Convex Optimization with Weakly Convex Constraints
A proximally constrained subgradient method finds a nearly stationary point for weakly convex objectives with weakly convex constraints in O(1/epsilon^4) deterministic and O~(1/epsilon^6) stochastic iterations.
-
Stochastic Optimization for Non-convex Inf-Projection Problems
The paper provides stochastic algorithms with O(1/epsilon^{4/v}) iteration complexity for finding near-stationary points of non-convex inf-projection objectives, with a variance-regularization application.
Discussion (0). Continue with ORCID to comment.