Constrained Convex Minimization via Model-Based Excessive Gap
Abstract
We introduce a model-based excessive gap technique to analyze first-order primal- dual methods for constrained convex minimization. As a result, we construct first- order primal-dual methods with optimal convergence rates on the primal objec- tive residual and the primal feasibility gap of their iterates separately. Through a dual smoothing and prox-center selection strategy, our framework subsumes the augmented Lagrangian, alternating direction, and dual fast-gradient methods as special cases, where our rates apply.
Cite
Text
Tran-Dinh and Cevher. "Constrained Convex Minimization via Model-Based Excessive Gap." Neural Information Processing Systems, 2014.Markdown
[Tran-Dinh and Cevher. "Constrained Convex Minimization via Model-Based Excessive Gap." Neural Information Processing Systems, 2014.](https://mlanthology.org/neurips/2014/trandinh2014neurips-constrained/)BibTeX
@inproceedings{trandinh2014neurips-constrained,
title = {{Constrained Convex Minimization via Model-Based Excessive Gap}},
author = {Tran-Dinh, Quoc and Cevher, Volkan},
booktitle = {Neural Information Processing Systems},
year = {2014},
pages = {721-729},
url = {https://mlanthology.org/neurips/2014/trandinh2014neurips-constrained/}
}