Approximating Concavely Parameterized Optimization Problems

Abstract

We consider an abstract class of optimization problems that are parameterized concavely in a single parameter, and show that the solution path along the parameter can always be approximated with accuracy $\varepsilon >0$ by a set of size $O(1/\sqrt{\varepsilon})$. A lower bound of size $\Omega (1/\sqrt{\varepsilon})$ shows that the upper bound is tight up to a constant factor. We also devise an algorithm that calls a step-size oracle and computes an approximate path of size $O(1/\sqrt{\varepsilon})$. Finally, we provide an implementation of the oracle for soft-margin support vector machines, and a parameterized semi-definite program for matrix completion.

Cite

Text

Giesen et al. "Approximating Concavely Parameterized Optimization Problems." Neural Information Processing Systems, 2012.

Markdown

[Giesen et al. "Approximating Concavely Parameterized Optimization Problems." Neural Information Processing Systems, 2012.](https://mlanthology.org/neurips/2012/giesen2012neurips-approximating/)

BibTeX

@inproceedings{giesen2012neurips-approximating,
  title     = {{Approximating Concavely Parameterized Optimization Problems}},
  author    = {Giesen, Joachim and Mueller, Jens and Laue, Soeren and Swiercy, Sascha},
  booktitle = {Neural Information Processing Systems},
  year      = {2012},
  pages     = {2105-2113},
  url       = {https://mlanthology.org/neurips/2012/giesen2012neurips-approximating/}
}