Corpus ID: 9079902

Fast, Provable Algorithms for Isotonic Regression in all L_p-norms

@inproceedings{Kyng2015FastPA,
  title={Fast, Provable Algorithms for Isotonic Regression in all L_p-norms},
  author={Rasmus Kyng and A. Rao and Sushant Sachdeva},
  booktitle={NIPS},
  year={2015}
}

Rasmus Kyng, A. Rao, Sushant Sachdeva

Published in NIPS 2015

Mathematics, Computer Science

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed

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.