Sample Complexity for Generative Learning of Quantum Measurement Data

arXiv:2610.38028 · quant-ph, cond-mat.stat-mech · Submitted 2026-10-27 · Read on arXiv

quant-ph, cond-mat.stat-mech

Submitted: 2026-10-27

Updated: 2026-10-30

Comments: 14 pages, 8 figures

License: http://creativecommons.org/licenses/by/4.0/

The gist: Generative learning of a quantum measurement distribution from finite data requires choosing a model capacity that balances representation accuracy against estimation cost.

Terminology

Abstract

Generative learning of a quantum measurement distribution from finite data requires choosing a model capacity that balances representation accuracy against estimation cost. We develop a bias-variance framework that decomposes the expected population Kullback-Leibler error at model capacity s and sample size N as E(s,N)=B(s)+V(s,N), with representation bias B and a variance term V capturing the mean estimation error. In the well-sampled regime, V(s,N) [NC(s)]-1, and exponential or algebraic laws for B and C yield four scaling templates for the optimal error, from inverse powers of N to inverse powers of N. For local autoregressive models, the context radius sets the model capacity, and B is the summed conditional mutual information lost by truncating the context. For a smoothed histogram learner, we derive an exact finite-sample estimation cost that accounts for rarely observed contexts and recovers the parameter-count law in the well-sampled regime. For transverse-field Ising Born distributions, the independently evaluated bias and estimation cost predict both the optimal context radius and the optimal error. In the well-sampled regime, the estimation cost grows exponentially with context radius. Its competition with approximately exponential bias decay in the gapped regimes predicts power-law error decay in N, while algebraic bias decay at criticality predicts asymptotic inverse-power decay in N. Bulk-site results are consistent with the corresponding finite-sample predictions. These results connect the structure of quantum measurement distributions to the model capacity justified by finite data.

Related papers