Universality of Many-body Projected Ensemble for Learning Quantum Data Distribution

ICLR 2026 Conference Submission15899 Authors

Keywords: universality approximation theorem, quantum data distribution, many-body projected ensemble

TL;DR: A proof for universal approximation theorem to express quantum data distribution

Abstract: Generating quantum data by learning the underlying quantum distribution poses challenges in both theoretical and practical scenarios, yet it is a critical task for understanding quantum systems. A fundamental question in quantum machine learning (QML) is the universality of approximation: whether a parameterized QML model can approximate any quantum distribution. We address this question by proving a universality theorem for the Many-body Projected Ensemble (MPE) framework, a method for quantum state design that uses a single many-body wave function to prepare random states. This demonstrates that MPE can approximate any distribution of pure states within a 1-Wasserstein distance error. This theorem provides a rigorous guarantee of universal expressivity, addressing key theoretical gaps in QML. For practicality, we propose an Incremental MPE variant with layerwise training to mitigate barren plateaus and enhance scalability. Numerical experiments on clustered quantum states and quantum chemistry datasets validate MPE's efficacy in learning complex quantum data distributions.

Primary Area: learning theory

Submission Number: 15899