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. |
Year | Venue | DocType |
---|---|---|
2016 | ICML | Conference |
Volume | Citations | PageRank |
abs/1602.05205 | 2 | 0.46 |
References | Authors | |
25 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Celestine Dunner | 1 | 12 | 6.99 |
Simone Forte | 2 | 7 | 0.98 |
Martin Takác | 3 | 752 | 49.49 |
Martin Jaggi | 4 | 852 | 54.16 |