2026/02/28 by Ait Haddou Marwan
Computer Science · Physics and Astronomy · #cs.LG #quant-ph
paper · pdf · doi:10.48550/arxiv.2602.14735
The manuscript is withdrawn because subsequent work showed that its central theoretical interpretation is incomplete. The relationship between local Pauli-weight contraction, measurement accessibility, and learnability requires a different theoretical framework. A substantially revised treatment is under preparation, and the current version should not be cited for these claims
arxiv created 2026/08/04 · arxiv updated 2026/08/05
The performance of quantum classifiers is typically analyzed through global state distinguishability or the trainability of variational models. This study investigates how much class information remains accessible under locality-constrained measurements in the presence of noise. The authors formulate binary quantum classification as constrained quantum state discrimination and introduce a locality-restricted distinguishability measure quantifying the maximum bias achievable by observables acting on at most k subsystems. For n-qubit systems subject to independent depolarizing noise, the locally accessible signal is governed by a Pauli-weight-dependent contraction mechanism. This motivates a computable predictor, the k-local Pauli-accessible amplitude Ak(p), which lower bounds the optimal k-local classification advantage. Numerical experiments on four-qubit encodings demonstrate quantitative agreement between empirical accuracy and the prediction across noise levels. The research identifies an operational breakdown threshold where k-local classifiers become indistinguishable from random guessing despite persistent global distinguishability.