Duality and the Continuous Graphical Model

Abstract

Inspired by the Linear Programming based algorithms for discrete MRFs, we show how a corresponding infinite-dimensional dual for continuous-state MRFs can be approximated by a hierarchy of tractable relaxations. This hierarchy of dual programs includes as a special case the methods of Peng et al. [17] and Zach & Kohli [33]. We give approximation bounds for the tightness of our construction, study their relationship to discrete MRFs and give a generic optimization algorithm based on Nesterov’s dual-smoothing method [16].

Cite

Text

Fix and Agarwal. "Duality and the Continuous Graphical Model." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10578-9_18

Markdown

[Fix and Agarwal. "Duality and the Continuous Graphical Model." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/fix2014eccv-duality/) doi:10.1007/978-3-319-10578-9_18

BibTeX

@inproceedings{fix2014eccv-duality,
  title     = {{Duality and the Continuous Graphical Model}},
  author    = {Fix, Alexander and Agarwal, Sameer},
  booktitle = {European Conference on Computer Vision},
  year      = {2014},
  pages     = {266-281},
  doi       = {10.1007/978-3-319-10578-9_18},
  url       = {https://mlanthology.org/eccv/2014/fix2014eccv-duality/}
}