Deterministic Distributed Algorithms and Lower Bounds in the Hybrid Model

TL;DR

This paper explores the capabilities of hybrid networks combining local and limited all-to-all communication, providing deterministic algorithms for fundamental problems like shortest paths and min-cut, and establishing lower bounds on computing graph radius.

Contribution

It introduces deterministic algorithms for sparse graphs in the hybrid model, achieves near-optimal approximations for shortest paths, and proves lower bounds for graph radius computations.

Findings

Deterministic $ ilde{O}( oot{n})$-round algorithms for sparse graphs.

Approximate shortest path algorithms matching randomized performance.

Lower bounds of $ ilde{ ext{O}}(n^{1/3})$ rounds for graph radius.

Abstract

The $\hybrid$ model was recently introduced by Augustine et al. \cite{DBLP:conf/soda/AugustineHKSS20} in order to characterize from an algorithmic standpoint the capabilities of networks which combine multiple communication modes. Concretely, it is assumed that the standard $\local$ model of distributed computing is enhanced with the feature of all-to-all communication, but with very limited bandwidth, captured by the node-capacitated clique ($\ncc$). In this work we provide several new insights on the power of hybrid networks for fundamental problems in distributed algorithms. First, we present a deterministic algorithm which solves any problem on a sparse $n$-node graph in $\widetilde{\mathcal{O}}(\sqrt{n})$ rounds of $\hybrid$. We combine this primitive with several sparsification techniques to obtain efficient distributed algorithms for general graphs. Most notably, for the all-pairs shortest paths problem we give deterministic $(1 + \epsilon)$- and $\log n/\log \log n$-approximate algorithms for unweighted and weighted graphs respectively with round complexity $\widetilde{\mathcal{O}}(\sqrt{n})$ in $\hybrid$, closely matching the performance of the state of the art randomized algorithm of Kuhn and Schneider \cite{10.1145/3382734.3405719}. Moreover, we make a connection with the Ghaffari-Haeupler framework of low-congestion shortcuts \cite{DBLP:conf/soda/GhaffariH16}, leading -- among others -- to a $(1 + \epsilon)$-approximate algorithm for Min-Cut after $\log^{\mathcal{O}(1)}n$ rounds, with high probability, even if we restrict local edges to transfer $\mathcal{O}(\log n)$-bits per round. Finally, we prove via a reduction from the set disjointness problem that $\widetilde{\Omega}(n^{1/3})$ rounds are required to determine the radius of an unweighted graph, as well as a $(3/2 - \epsilon)$-approximation for weighted graphs.