Information-Theoretic Limits of Quantum Learning via Data Compression

TL;DR

This paper introduces a quantum data compression framework to analyze the limits of quantum machine learning, providing lower bounds on sample complexity and data size for learning tasks, with implications for security in delegated quantum computation.

Contribution

It develops a systematic quantum lossy data compression approach to establish fundamental limits on quantum learning and secure delegated quantum computation.

Findings

Lower bounds on quantum sample complexity for Zipf-distributed data

Optimal quantum data size for learning linear functions

Enhanced security guarantees in measurement-based quantum delegation

Abstract

Understanding the power of quantum data in machine learning is central to many proposed applications of quantum technologies. While access to quantum data can offer exponential advantages for carefully designed learning tasks and often under strong assumptions on the data distribution, it remains an open question whether such advantages persist in less structured settings and under more realistic, naturally occurring distributions. Motivated by these practical concerns, we introduce a systematic framework based on quantum lossy data compression to bound the power of quantum data in the context of probably approximately correct (PAC) learning. Specifically, we provide lower bounds on the sample complexity of quantum learners for arbitrary functions when data is drawn from Zipf's distribution, a widely used model for the empirical distributions of real-world data. We also establish lower bounds on the size of quantum input data required to learn linear functions, thereby proving the optimality of previous positive results. Beyond learning theory, we show that our framework has applications in secure delegated quantum computation within the measurement-based quantum computation (MBQC) model. In particular, we constrain the amount of private information the server can infer, strengthening the security guarantees of the delegation protocol proposed in (Mantri et al., PRX, 2017).