Toward Interpretable Quantum Generators for Financial Returns through Problem-Informed Circuit Design
Abstract
When used as function approximators, quantum circuits often lack interpretability and face a fundamental trade-off between expressivity and trainability. We propose a problem-informed framework for financial return generation that uses relational structure and symmetry-inspired parameter sharing to guide the construction of quantum circuits with few trainable parameters and empirically testable operator roles. We evaluate three quantum generator architectures, referred to as ZZ, directed ZZ-CRX, and structured time evolution, within a hybrid Wasserstein quantum generative adversarial network trained to generate 16-step Bitcoin return windows. Across circuits with one to four layers and one to eight trainable coefficients, these generators recover meaningful marginal and temporal distributional features, while single-layer configurations remain competitive with deeper variants. Across matched depths, independently trained ZZ-CRX configurations exhibit a predominantly downward shift in median leverage relative to ZZ, consistent with the intended directional role of the controlled-rotation construction. The small number of coefficients also enables direct landscape analysis, revealing competing parameter preferences between marginal and temporal objectives and helping to explain the difficulty of finding parameter settings that perform well on both. These results provide an initial demonstration that structural assumptions can guide the design of compact quantum generators and link circuit architecture to observable statistical behaviour, motivating more systematic and parameter-efficient approaches to quantum circuit construction.
Related
- [SUPERSEDED] Physics-Informed AI and Quantum Technologies for Certifiable Real-Time Control of Compact Fusion Generators
- Physics-informed interpretable forms for dipole resonances and quantities relevant for astrophysics
- The Differential Structure of Generators of KMS-Symmetric Quantum Markov Semigroups
- Time-optimal quantum dynamics under fixed-norm generators
- From Local Atomic Motifs to Thermodynamic State: An Interpretable Physics-Informed Framework for Cu-Zr Metallic Glasses
BibTeX
@misc{guan2026toward,
title = {{Toward Interpretable Quantum Generators for Financial Returns through Problem-Informed Circuit Design}},
author = {Huijie Guan and Xuanhao Wang and Shengbin Wang and Jiale Zhang and Jian Ding and Shuxin Xie and Dongdong Li and Jianjian Gao and Hantao Sun and Wenhao Chu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.17632},
eprint = {2610.17632},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.17632},
note = {CC0},
}
RIS
TY - UNPB
TI - Toward Interpretable Quantum Generators for Financial Returns through Problem-Informed Circuit Design
AU - Huijie Guan
AU - Xuanhao Wang
AU - Shengbin Wang
AU - Jiale Zhang
AU - Jian Ding
AU - Shuxin Xie
AU - Dongdong Li
AU - Jianjian Gao
AU - Hantao Sun
AU - Wenhao Chu
PY - 2026
DA - 2026/10/13
PB - arXiv
DO - 10.48550/arxiv.2610.17632
UR - https://arxiv.org/abs/2610.17632
AB - When used as function approximators, quantum circuits often lack interpretability and face a fundamental trade-off between expressivity and trainability. We propose a problem-informed framework for financial return generation that uses relational structure and symmetry-inspired parameter sharing to guide the construction of quantum circuits with few trainable parameters and empirically testable operator roles. We evaluate three quantum generator architectures, referred to as ZZ, directed ZZ-CRX, and structured time evolution, within a hybrid Wasserstein quantum generative adversarial network trained to generate 16-step Bitcoin return windows. Across circuits with one to four layers and one to eight trainable coefficients, these generators recover meaningful marginal and temporal distributional features, while single-layer configurations remain competitive with deeper variants. Across matched depths, independently trained ZZ-CRX configurations exhibit a predominantly downward shift in median leverage relative to ZZ, consistent with the intended directional role of the controlled-rotation construction. The small number of coefficients also enables direct landscape analysis, revealing competing parameter preferences between marginal and temporal objectives and helping to explain the difficulty of finding parameter settings that perform well on both. These results provide an initial demonstration that structural assumptions can guide the design of compact quantum generators and link circuit architecture to observable statistical behaviour, motivating more systematic and parameter-efficient approaches to quantum circuit construction.
ER -