Exponential separations between classical and quantum learners
This work addresses the problem of demonstrating quantum learning advantages for more realistic datasets, potentially impacting researchers in quantum machine learning and computational theory, though it is incremental in building on existing theory.
The paper tackles the challenge of identifying learning problems where quantum algorithms can achieve provable exponential speedups over classical ones, presenting two new separations where classical difficulty lies in function identification rather than evaluation, and exploring quantum-generated data scenarios that suggest advantages in natural settings like condensed matter physics.
Despite significant effort, the quantum machine learning community has only demonstrated quantum learning advantages for artificial cryptography-inspired datasets when dealing with classical data. In this paper we address the challenge of finding learning problems where quantum learning algorithms can achieve a provable exponential speedup over classical learning algorithms. We reflect on computational learning theory concepts related to this question and discuss how subtle differences in definitions can result in significantly different requirements and tasks for the learner to meet and solve. We examine existing learning problems with provable quantum speedups and find that they largely rely on the classical hardness of evaluating the function that generates the data, rather than identifying it. To address this, we present two new learning separations where the classical difficulty primarily lies in identifying the function generating the data. Furthermore, we explore computational hardness assumptions that can be leveraged to prove quantum speedups in scenarios where data is quantum-generated, which implies likely quantum advantages in a plethora of more natural settings (e.g., in condensed matter and high energy physics). We also discuss the limitations of the classical shadow paradigm in the context of learning separations, and how physically-motivated settings such as characterizing phases of matter and Hamiltonian learning fit in the computational learning framework.