Title | ||
---|---|---|
Alternating Structure-Adapted Proximal Gradient Descent for Nonconvex Nonsmooth Block-Regularized Problems. |
Abstract | ||
---|---|---|
There has been increasing interest in constrained nonconvex regularized block optimization problems. We introduce an approach that enables complex application-dependent regularization terms to be used. The proposed alternating structure-adapted proximal gradient descent algorithm enjoys simple well-defined updates and is proved to be a value-convergent descent scheme in general cases. Global convergence of the algorithm to a critical point is proved using the so-called Kurdyka-Lojasiewicz property. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1137/17M1142624 | SIAM JOURNAL ON OPTIMIZATION |
Keywords | Field | DocType |
alternating minimization,block coordinate descent,global convergence,Kurdyka-Lojasiewicz property,nonconvex-nonsmooth optimization,forward-backward splitting,proximal gradient descent,subdifferential calculus | Gradient descent,Mathematical optimization,Regularization (mathematics),Optimization problem,Mathematics | Journal |
Volume | Issue | ISSN |
29 | 3 | 1052-6234 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mila Nikolova | 1 | 1792 | 105.71 |
Pauline Tan | 2 | 0 | 0.68 |