English

Primal-Dual Rates and Certificates

Machine Learning 2016-06-06 v2 Optimization and Control

Abstract

We propose an algorithm-independent framework to equip existing optimization methods with primal-dual certificates. Such certificates and corresponding rate of convergence guarantees are important for practitioners to diagnose progress, in particular in machine learning applications. We obtain new primal-dual convergence rates, e.g., for the Lasso as well as many L1, Elastic Net, group Lasso and TV-regularized problems. The theory applies to any norm-regularized generalized linear model. Our approach provides efficiently computable duality gaps which are globally defined, without modifying the original problems in the region of interest.

Keywords

Cite

@article{arxiv.1602.05205,
  title  = {Primal-Dual Rates and Certificates},
  author = {Celestine Dünner and Simone Forte and Martin Takáč and Martin Jaggi},
  journal= {arXiv preprint arXiv:1602.05205},
  year   = {2016}
}

Comments

appearing at ICML 2016 - Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA, 2016. JMLR: W&CP volume 48

R2 v1 2026-06-22T12:51:44.652Z