Optimal Non-Adaptive Probabilistic Group Testing in General Sparsity Regimes

TL;DR

This paper determines the minimal number of tests needed for noiseless non-adaptive probabilistic group testing across all sparsity regimes, extending previous results and establishing optimality of individual testing in dense regimes.

Contribution

It provides a unified asymptotic characterization of the minimal tests required for all sparsity levels, improving upon prior bounds and removing restrictive assumptions.

Findings

Minimal tests scale as  C_{k,n} k \u2206 n, matching n in dense regimes.

Algorithmic analysis based on a slight modification of the Definite Defectives algorithm.

Demonstrates individual testing is optimal in very dense regimes for any non-zero success probability.

Abstract

In this paper, we consider the problem of noiseless non-adaptive probabilistic group testing, in which the goal is high-probability recovery of the defective set. We show that in the case of $n$ items among which $k$ are defective, the smallest possible number of tests equals $\min\{ C_{k,n} k \log n, n\}$ up to lower-order asymptotic terms, where $C_{k,n}$ is a uniformly bounded constant (varying depending on the scaling of $k$ with respect to $n$) with a simple explicit expression. The algorithmic upper bound follows from a minor adaptation of an existing analysis of the Definite Defectives (DD) algorithm, and the algorithm-independent lower bound builds on existing works for the regimes $k \le n^{1-\Omega(1)}$ and $k = \Theta(n)$. In sufficiently sparse regimes (including $k = o\big( \frac{n}{\log n} \big)$), our main result generalizes that of Coja-Oghlan {\em et al.} (2020) by avoiding the assumption $k \le n^{1-\Omega(1)}$, whereas in sufficiently dense regimes (including $k = \omega\big( \frac{n}{\log n} \big)$), our main result shows that individual testing is asymptotically optimal for any non-zero target success probability, thus strengthening an existing result of Aldridge (2019) in terms of both the error probability and the assumed scaling of $k$.