New Frameworks for Offline and Streaming Coreset Constructions

A coreset for a set of points is a small subset of weighted points that approximately preserves important properties of the original set. Specifically, if P is a set of points, Q is a set of queries, and f:P× Q→ℝ is a cost function, then a set Ssubseteq P with weights w:P→[0,∞) is an ε-coreset for some parameter ε>0 if sums∈ Sw(s)f(s,q) is a (1+ε) multiplicative approximation to sump∈ Pf(p,q) for all q∈ Q. Coresets are used to solve fundamental problems in machine learning under various big data models of computation. Many of the suggested coresets in the recent decade used, or could have used a general framework for constructing coresets whose size depends quadratically on what is known as total sensitivity t. In this paper we improve this bound from O(t2) to O(tlog t). Thus our results imply more space efficient solutions to a number of problems, including projective clustering, k-line clustering, and subspace approximation. Moreover, we generalize the notion of sensitivity sampling for sup-sampling that supports non-multiplicative approximations, negative cost functions and more. The main technical result is a generic reduction to the sample complexity of learning a class of functions with bounded VC dimension. We show that obtaining an (nu,α)-sample for this class of functions with appropriate parameters nu and α suffices to achieve space efficient ε-coresets. Our result implies more efficient coreset constructions for a number of interesting problems in machine learning; we show applications to k-median/k-means, k-line clustering, j-subspace approximation, and the integer (j,k)-projective clustering problem.