Provable Approximations for Constrained $\ell_p$ Regression

Abstract: The $\ell_p$ linear regression problem is to minimize $f(x)=||Ax-b||_p$ over $x\in\mathbb{R}<sup>d$, where $A\in\mathbb{R}^{n\times d}$, $b\in \mathbb{R}<sup>n$, and $p&gt;0$. To avoid overfitting and bound $||x||_2$, the constrained $\ell_p$ regression minimizes $f(x)$ over every unit vector $x\in\mathbb{R}<sup>d$. This makes the problem non-convex even for the simplest case $d=p=2$. Instead, ridge regression is used to minimize the Lagrange form $f(x)+\lambda ||x||_2$ over $x\in\mathbb{R}<sup>d$, which yields a convex problem in the price of calibrating the regularization parameter $\lambda&gt;0$. We provide the first provable constant factor approximation algorithm that solves the constrained $\ell_p$ regression directly, for every constant $p,d\geq 1$. Using core-sets, its running time is $O(n \log n)$ including extensions for streaming and distributed (big) data. In polynomial time, it can handle outliers, $p\in (0,1)$ and minimize $f(x)$ over every $x$ and permutation of rows in $A$. Experimental results are also provided, including open source and comparison to existing software.