Fast, Provable Algorithms for Isotonic Regression in all $\ell_{p}$-norms

Rasmus Kyng; Anup Rao; Sushant Sachdeva

Fast, Provable Algorithms for Isotonic Regression in all $\ell_{p}$-norms

Machine Learning 2015-11-12 v2 Data Structures and Algorithms Statistics Theory Statistics Theory

Authors: Rasmus Kyng , Anup Rao , Sushant Sachdeva

Abstract

Given a directed acyclic graph $G,$ and a set of values $y$ on the vertices, the Isotonic Regression of $y$ is a vector $x$ that respects the partial order described by $G,$ and minimizes $||x-y||,$ for a specified norm. This paper gives improved algorithms for computing the Isotonic Regression for all weighted $\ell_{p}$ -norms with rigorous performance guarantees. Our algorithms are quite practical, and their variants can be implemented to run fast in practice.

Keywords

isotonic regression directed acyclic graph ell_p-norms performance guarantees algorithms

Cite

@article{arxiv.1507.00710,
  title  = {Fast, Provable Algorithms for Isotonic Regression in all $\ell_{p}$-norms},
  author = {Rasmus Kyng and Anup Rao and Sushant Sachdeva},
  journal= {arXiv preprint arXiv:1507.00710},
  year   = {2015}
}

Fast, Provable Algorithms for Isotonic Regression in all $\ell_{p}$-norms

Abstract

Keywords

Cite

Related papers