Hierarchy of discriminative power and complexity in learning quantum ensembles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Jian, Li, Pengtao, Chen, Xiaohui, Zhuang, Quntao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910004967112704
author Yao, Jian
Li, Pengtao
Chen, Xiaohui
Zhuang, Quntao
author_facet Yao, Jian
Li, Pengtao
Chen, Xiaohui
Zhuang, Quntao
contents Distance metrics are central to machine learning, yet distances between ensembles of quantum states remain poorly understood due to fundamental quantum measurement constraints. We introduce a hierarchy of integral probability metrics, termed MMD-$k$, which generalizes the maximum mean discrepancy to quantum ensembles and exhibit a strict trade-off between discriminative power and statistical efficiency as the moment order $k$ increases. For pure-state ensembles of size $N$, estimating MMD-$k$ using experimentally feasible SWAP-test-based estimators requires $Θ(N^{2-2/k})$ samples for constant $k$, and $Θ(N^3)$ samples to achieve full discriminative power at $k = N$. In contrast, the quantum Wasserstein distance attains full discriminative power with $Θ(N^2 \log N)$ samples. These results provide principled guidance for the design of loss functions in quantum machine learning, which we illustrate in the training quantum denoising diffusion probabilistic models.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22005
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hierarchy of discriminative power and complexity in learning quantum ensembles
Yao, Jian
Li, Pengtao
Chen, Xiaohui
Zhuang, Quntao
Quantum Physics
Statistics Theory
Machine Learning
Distance metrics are central to machine learning, yet distances between ensembles of quantum states remain poorly understood due to fundamental quantum measurement constraints. We introduce a hierarchy of integral probability metrics, termed MMD-$k$, which generalizes the maximum mean discrepancy to quantum ensembles and exhibit a strict trade-off between discriminative power and statistical efficiency as the moment order $k$ increases. For pure-state ensembles of size $N$, estimating MMD-$k$ using experimentally feasible SWAP-test-based estimators requires $Θ(N^{2-2/k})$ samples for constant $k$, and $Θ(N^3)$ samples to achieve full discriminative power at $k = N$. In contrast, the quantum Wasserstein distance attains full discriminative power with $Θ(N^2 \log N)$ samples. These results provide principled guidance for the design of loss functions in quantum machine learning, which we illustrate in the training quantum denoising diffusion probabilistic models.
title Hierarchy of discriminative power and complexity in learning quantum ensembles
topic Quantum Physics
Statistics Theory
Machine Learning
url https://arxiv.org/abs/2601.22005