Online hitting set of $d$-dimensional fat objects

TL;DR

This paper introduces a deterministic online algorithm for the geometric hitting set problem involving fat objects in d-dimensional space, achieving a competitive ratio that is near-optimal and applicable to common shapes like disks and cubes.

Contribution

The paper presents a new online algorithm with a proven competitive ratio for the geometric hitting set problem involving fat objects, resolving open questions for specific shapes.

Findings

Algorithm achieves competitive ratio of ((4α+1)^{2d} log N).

No better ratio possible for fixed α and d.

Applicable to disks and d-cubes in 2D and higher dimensions.

Abstract

We consider an online version of the geometric minimum hitting set problem that can be described as a game between an adversary and an algorithm. For some integers $d$ and $N$, let $P$ be the set of points in $(0, N)^d$ with integral coordinates, and let $\mathcal{O}$ be a family of subsets of $P$, called objects. Both $P$ and $\mathcal{O}$ are known in advance by the algorithm and by the adversary. Then, the adversary gives some objects one by one, and the algorithm has to maintain a valid hitting set for these objects using points from $P$, with an immediate and irrevocable decision. We measure the performance of the algorithm by its competitive ratio, that is the ratio between the number of points used by the algorithm and the offline minimum hitting set for the sub-sequence of objects chosen by the adversary. We present a simple deterministic online algorithm with competitive ratio $((4\alpha+1)^{2d}\log N)$ when objects correspond to a family of $\alpha$-fat objects. Informally, $\alpha$-fatness measures how cube-like is an object. We show that no algorithm can achieve a better ratio when $\alpha$ and $d$ are fixed constants. In particular, our algorithm works for two-dimensional disks and $d$-cubes which answers two open questions from related previous papers in the special case where the set of points corresponds to all the points of integral coordinates with a fixed $d$-cube.