Quantum Proper Scoring Rules: Convex Duality, Bregman Risk, and the Coherence Gap
Abstract
We generalize proper scoring rules to the quantum domain, replacing probability distributions with density operators. We define Quantum Value Functionals via convex generators and establish a duality theory yielding proper quantum scoring rules using McCarthy's tangent-plane construction. We derive local minimax optimal bounds for quantum state tomography under these incentives, proving a Local Holevo-McCarthy Bound that explicitly links asymptotic risk to the Bogoliubov-Kubo-Mori metric and the Holevo bound. Furthermore, we establish an exact coherence floor that quantifies the irreducible excess score of fixed-basis forecasting strategies when phases are unknown (minimax over the phase orbit), proving a worst-case minimax floor of log d over the full state space. Our results contextualize fundamental sample complexity separations compared to optimal quantum estimation strategies and guide the design of incentive-compatible quantum data markets and robust quantum machine learning protocols.
Related
- A Strictly Proper Scoring-Rule Theory for Calibrating Stochastic Car-Following Models
- Quantum Error-Corrected Memories Keep Proper Time
- Quantum-Relativistic Anomalous Proper Time
- Problem-Specific Basis Quantum State Readout via Proper Orthogonal Decomposition
- Bethe Cycles, Frobenius Identities, and Quantum/Classical Duality
BibTeX
@misc{almasri2026quantum,
title = {{Quantum Proper Scoring Rules: Convex Duality, Bregman Risk, and the Coherence Gap}},
author = {M. W. AlMasri},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.05268},
eprint = {2605.05268},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.05268},
note = {CC BY-SA 4.0},
}
RIS
TY - UNPB
TI - Quantum Proper Scoring Rules: Convex Duality, Bregman Risk, and the Coherence Gap
AU - M. W. AlMasri
PY - 2026
DA - 2026/10/31
PB - arXiv
DO - 10.48550/arxiv.2605.05268
UR - https://arxiv.org/abs/2605.05268
AB - We generalize proper scoring rules to the quantum domain, replacing probability distributions with density operators. We define Quantum Value Functionals via convex generators and establish a duality theory yielding proper quantum scoring rules using McCarthy's tangent-plane construction. We derive local minimax optimal bounds for quantum state tomography under these incentives, proving a Local Holevo-McCarthy Bound that explicitly links asymptotic risk to the Bogoliubov-Kubo-Mori metric and the Holevo bound. Furthermore, we establish an exact coherence floor that quantifies the irreducible excess score of fixed-basis forecasting strategies when phases are unknown (minimax over the phase orbit), proving a worst-case minimax floor of log d over the full state space. Our results contextualize fundamental sample complexity separations compared to optimal quantum estimation strategies and guide the design of incentive-compatible quantum data markets and robust quantum machine learning protocols.
ER -