Horizon-Conditioned Proposals for Rare-Event Estimation with Variational and Hybrid Quantum Circuits
Proceedings of the AAAI Symposium Series · 06.11.2026 · 10 (1) · 854-861
DOI: 10.1609/aaaiss.v10i1.43499 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 06.11.2026. Verfasst von Victoria Zhang und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Claims about quantum learning models are difficult to audit when the function they approximate is rarely available for comparison. We construct a setting in which it is. For a finite-horizon hitting problem, the optimal importance-sampling proposal is the Doob h-transform, a value function conditioned on the number of steps remaining as well as on the current state. On an enumerable state space, both this target and the exact variance of any proposal derived from it are computable, allowing learning error to be measured rather than estimated. On this testbed, we compare three horizon encodings crossed with two symmetry sectors for Born machines, together with a hybrid dressed circuit and classical regressors, and study sensitivity to initialization, increasingly rare failure regimes, and finite measurement budgets. Within the architectures studied, the statewise-regressive models substantially outperform the Born-machine parameterizations. Across repeated initializations, additive time re-uploading remains the weakest of the tested horizon encodings, while a symmetry-restricted ansatz consistently improves median learning error despite using eight times fewer circuit parameters. Initialization strongly affects absolute performance, yet these broader design trends survive aggregation across seeds. Because both model classes produce normalized proposals, the observed gap reflects differences in parameterization and optimization rather than normalization alone. The two quantum architectures also exhibit distinct sensitivity to finite-shot readout, and across a γ-retuned family spanning p_T = 10^-2 to 10^-8 the classical-to-hybrid gap widens substantially. Together, these results show how an exactly evaluable rare-event benchmark can separate effects of representation, optimization, and measurement that are otherwise easy to conflate in quantum-learning comparisons.
Zitieren
APA
Zhang, V., Cao, P., & Srikant, R. (2026). Horizon-Conditioned Proposals for Rare-Event Estimation with Variational and Hybrid Quantum Circuits. Proceedings of the AAAI Symposium Series, 10(1), 854-861. https://doi.org/10.1609/aaaiss.v10i1.43499
Vancouver
Zhang V, Cao P, Srikant R. Horizon-Conditioned Proposals for Rare-Event Estimation with Variational and Hybrid Quantum Circuits. Proceedings of the AAAI Symposium Series. 2026;10(1):854-861. doi:10.1609/aaaiss.v10i1.43499
BibTeX
@article{Zhang2026,
author = {Zhang, Victoria and Cao, Phuong and Srikant, R.},
title = {Horizon-Conditioned Proposals for Rare-Event Estimation with Variational and Hybrid Quantum Circuits},
journal = {Proceedings of the AAAI Symposium Series},
year = {2026},
volume = {10},
number = {1},
pages = {854--861},
doi = {10.1609/aaaiss.v10i1.43499}
}
EUVIMED