The paper proves sublinear rates for coordinate subgradient descent, randomly permuted coordinate descent, and accelerated proximal point methods on structured nonconvex problems, but the accelerated DC method's inner-iteration complexity is not supported by the paper's own equations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficiency of Coordinate Descent Methods For Structured Nonconvex Optimization
The paper proves sublinear rates for coordinate subgradient descent, randomly permuted coordinate descent, and accelerated proximal point methods on structured nonconvex problems, but the accelerated DC method's inner-iteration complexity is not supported by the paper's own equations.