Quantum advantage and lower bounds in parallel query complexity

TL;DR

This paper demonstrates that quantum parallel query complexity can significantly outperform classical methods, revealing new separations and bounds, and challenging previous assumptions about the limitations of quantum advantage in total boolean functions.

Contribution

It introduces novel techniques and constructions showing unbounded quantum advantage in parallel query models, including for total functions, and establishes new lower bounds.

Findings

Unbounded quantum advantage over randomized for a total function.

Quantum advantage can occur solely due to parallelism, even without sequential advantage.

Polynomial separation between 2-round quantum and randomized complexities.

Abstract

It is well known that quantum, randomized and deterministic (sequential) query complexities are polynomially related for total boolean functions. We find that significantly larger separations between the parallel generalizations of these measures are possible. In particular, (1) We employ the cheatsheet framework to obtain an unbounded parallel quantum query advantage over its randomized analogue for a total function, falsifying a conjecture of Jeffery et al. 2017 (arXiv:1309.6116). (2) We strengthen (1) by constructing a total function which exhibits an unbounded parallel quantum query advantage despite having no sequential advantage, suggesting that genuine quantum advantage could occur entirely due to parallelism. (3) We construct a total function that exhibits a polynomial separation between 2-round quantum and randomized query complexities, contrasting a result of Montanaro in 2010 (arXiv:1001.0018) that there is at most a constant separation for 1-round (nonadaptive) algorithms. (4) We develop a new technique for deriving parallel quantum lower bounds from sequential upper bounds. We employ this technique to give lower bounds for Boolean symmetric functions and read-once formulas, ruling out large parallel query advantages for them. We also provide separations between randomized and deterministic parallel query complexities analogous to items (1)-(3).