Witnessing Quantum Bayesian Inference beyond Classical Learning
Abstract
Can an agent's predictions reveal whether its reasoning is based on a classical or a quantum model? Using known results on matrix factorizations, here we show that quantum Bayesian retrodiction can produce one-step-ahead forecasts incompatible with every classical Bayesian explanation based on learning about a fixed but unknown sampling law from conditionally independent observations. The separation has a sharp threshold in the number of outcomes: for any measurement with at most four outcomes, the quantum predictions admit a classical realization, irrespective of the prior state and the finite Hilbert-space dimension, whereas a five-outcome measurement on a single qubit already violates an explicit classical bound. This bound holds for arbitrary classical latent states, prior probabilities, and sampling laws, and involves only the agent's initial and updated predictions. Thus, in this setting, quantum Bayesian retrodiction is strictly more expressive than classical Bayesian learning, and this difference can be witnessed without observing or specifying the agent's internal description.
Related
- The Wrapped Q-Lindley Distribution: A New Circular Model with Statistical Properties, Classical and Bayesian Inference, and Applications to Directional Data
- Efficient Bayesian inference for multiple network data
- Bayesian inference under model misspecification
- Modern Bayesian Modeling and Inference
- Kumaraswamy-Teissier Distribution: Bayesian and Non-Bayesian Inference, Regression Modeling and Climate Application
BibTeX
@misc{buscemi2026witnessing,
title = {{Witnessing Quantum Bayesian Inference beyond Classical Learning}},
author = {Francesco Buscemi},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.09293},
eprint = {2610.09293},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.09293},
}
RIS
TY - UNPB
TI - Witnessing Quantum Bayesian Inference beyond Classical Learning
AU - Francesco Buscemi
PY - 2026
DA - 2026/10/08
PB - arXiv
DO - 10.48550/arxiv.2610.09293
UR - https://arxiv.org/abs/2610.09293
AB - Can an agent's predictions reveal whether its reasoning is based on a classical or a quantum model? Using known results on matrix factorizations, here we show that quantum Bayesian retrodiction can produce one-step-ahead forecasts incompatible with every classical Bayesian explanation based on learning about a fixed but unknown sampling law from conditionally independent observations. The separation has a sharp threshold in the number of outcomes: for any measurement with at most four outcomes, the quantum predictions admit a classical realization, irrespective of the prior state and the finite Hilbert-space dimension, whereas a five-outcome measurement on a single qubit already violates an explicit classical bound. This bound holds for arbitrary classical latent states, prior probabilities, and sampling laws, and involves only the agent's initial and updated predictions. Thus, in this setting, quantum Bayesian retrodiction is strictly more expressive than classical Bayesian learning, and this difference can be witnessed without observing or specifying the agent's internal description.
ER -