Rethink the Role of Deep Learning towards Large-scale Quantum Systems

TL;DR

This paper systematically benchmarks deep learning against traditional machine learning for quantum ground state tasks, revealing that simpler models often perform equally well or better, questioning the necessity of deep learning in this domain.

Contribution

It provides a fair comparison of DL and ML models in quantum ground state tasks, highlighting that DL models may not always be necessary, and offers insights into their effective use.

Findings

ML models perform comparably or better than DL models.

Measurement input features have minimal impact on DL performance.

Deep learning may not be essential for certain quantum system learning tasks.

Abstract

Characterizing the ground state properties of quantum systems is fundamental to capturing their behavior but computationally challenging. Recent advances in AI have introduced novel approaches, with diverse machine learning (ML) and deep learning (DL) models proposed for this purpose. However, the necessity and specific role of DL models in these tasks remain unclear, as prior studies often employ varied or impractical quantum resources to construct datasets, resulting in unfair comparisons. To address this, we systematically benchmark DL models against traditional ML approaches across three families of Hamiltonian, scaling up to 127 qubits in three crucial ground-state learning tasks while enforcing equivalent quantum resource usage. Our results reveal that ML models often achieve performance comparable to or even exceeding that of DL approaches across all tasks. Furthermore, a randomization test demonstrates that measurement input features have minimal impact on DL models' prediction performance. These findings challenge the necessity of current DL models in many quantum system learning scenarios and provide valuable insights into their effective utilization.