`

Timezone: »

Poster
Fast, Provable Algorithms for Isotonic Regression in all L_p-norms
Rasmus Kyng · Anup Rao · Sushant Sachdeva

Tue Dec 08 04:00 PM -- 08:59 PM (PST) @ 210 C #86 #None
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.