Simultaneous Greedys: A Swiss Army Knife for Constrained Submodular Maximization

In this paper, we present SimultaneousGreedys, a deterministic algorithm for constrained submodular maximization. At a high level, the algorithm maintains $\ell$ solutions and greedily updates them in a simultaneous fashion, rather than a sequential one. SimultaneousGreedys achieves the tightest known approximation guarantees for both $k$-extendible systems and the more general $k$-systems, which are $(k+1)^2/k = k + \mathcal{O}(1)$ and $(1 + \sqrt{k+2})^2 = k + \mathcal{O}(\sqrt{k})$, respectively. This is in contrast to previous algorithms, which are designed to provide tight approximation guarantees in one setting, but not both. Furthermore, these approximation guarantees further improve to $k+1$ when the objective is monotone. We demonstrate that the algorithm may be modified to run in nearly linear time with an arbitrarily small loss in the approximation. This leads to the first nearly linear time algorithm for submodular maximization over $k$-extendible systems and $k$-systems. Finally, the technique is flexible enough to incorporate the intersection of $m$ additional knapsack constraints, while retaining similar approximation guarantees, which are roughly $k + 2m + \mathcal{O}(\sqrt{k+m})$ for $k$-systems and $k+2m + \mathcal{O}(\sqrt{m})$ for $k$-extendible systems. To complement our algorithmic contributions, we provide a hardness result which states that no algorithm making polynomially many queries to the value and independence oracles can achieve an approximation better than $k + 1/2 + \varepsilon$.