Develops constant-stepsize and auto-conditioned projected gradient methods plus stochastic variants that achieve new iteration complexity bounds for finding approximate stationary points in nonconvex smooth optimization.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.OC 2verdicts
UNVERDICTED 2representative citing papers
Establishes iteration complexity for proximal bundle methods on hybrid weakly convex composite optimization problems via a unified framework with verifiable stationarity.
citing papers explorer
-
Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes
Develops constant-stepsize and auto-conditioned projected gradient methods plus stochastic variants that achieve new iteration complexity bounds for finding approximate stationary points in nonconvex smooth optimization.
-
Proximal bundle methods for hybrid weakly convex composite optimization problems
Establishes iteration complexity for proximal bundle methods on hybrid weakly convex composite optimization problems via a unified framework with verifiable stationarity.