Prospects for quantum advantage in machine learning from the representability of functions

TL;DR

This paper develops a framework linking quantum circuit structures to the functions they can learn, clarifying when quantum models outperform classical ones and identifying pathways to dequantization in machine learning.

Contribution

It introduces a theoretical framework connecting quantum circuit properties to function learnability, aiding the identification of models with potential quantum advantage.

Findings

Circuit depth and non-Clifford gates determine classical simulability.

Many existing simulation methods exploit pathways to dequantization.

The framework distinguishes fully simulatable models from robustly quantum ones.

Abstract

Demonstrating quantum advantage in machine learning tasks requires navigating a complex landscape of proposed models and algorithms. To bring clarity to this search, we introduce a framework that connects the structure of parametrized quantum circuits to the mathematical nature of the functions they can actually learn. Within this framework, we show how fundamental properties, like circuit depth and non-Clifford gate count, directly determine whether a model's output leads to efficient classical simulation or surrogation. We argue that this analysis uncovers common pathways to dequantization that underlie many existing simulation methods. More importantly, it reveals critical distinctions between models that are fully simulatable, those whose function space is classically tractable, and those that remain robustly quantum. This perspective provides a conceptual map of this landscape, clarifying how different models relate to classical simulability and pointing to where opportunities for quantum advantage may lie.