# Oracles and query lower bounds in generalised probabilistic theories

## TL;DR

This paper explores how interference in generalised probabilistic theories influences computational power, establishing oracle models and lower bounds that extend quantum computational limits within a broader theoretical framework.

## Contribution

It introduces an oracle model for generalised probabilistic theories satisfying key physical principles and links interference hierarchy to query complexity lower bounds.

## Key findings

- Lower bounds on query complexity scale with interference order
- Oracle models are well-defined under causality, purification, and symmetry principles
- Higher-order interference may provide computational resources beyond quantum computing

## Abstract

We investigate the connection between interference and computational power within the operationally defined framework of generalised probabilistic theories. To compare the computational abilities of different theories within this framework we show that any theory satisfying three natural physical principles possess a well-defined oracle model. Indeed, we prove a subroutine theorem for oracles in such theories which is a necessary condition for the oracle to be well-defined. The three principles are: causality (roughly, no signalling from the future), purification (each mixed state arises as the marginal of a pure state of a larger system), and strong symmetry existence of non-trivial reversible transformations). Sorkin has defined a hierarchy of conceivable interference behaviours, where the order in the hierarchy corresponds to the number of paths that have an irreducible interaction in a multi-slit experiment. Given our oracle model, we show that if a classical computer requires at least n queries to solve a learning problem, then the corresponding lower bound in theories lying at the kth level of Sorkin's hierarchy is n/k. Hence, lower bounds on the number of queries to a quantum oracle needed to solve certain problems are not optimal in the space of all generalised probabilistic theories, although it is not yet known whether the optimal bounds are achievable in general. Hence searches for higher-order interference are not only foundationally motivated, but constitute a search for a computational resource beyond that offered by quantum computation.