Learning to Program Adaptive Non-Local Observables for Machine Learning
Abstract
Quantum neural networks (QNNs) are typically built from variational quantum circuits (VQCs), which are limited by local measurements. Adaptive non-local observables (ANO) address this by jointly optimizing circuit parameters and multi-qubit measurements. However, existing ANO-based VQCs learn only a single static observable that remains invariant across all inputs. We propose QFWP-ANO, a novel architecture which employs a classical hypernetwork to dynamically program VQC parameters and/or non-local observables conditioned on each input. On multivariate time-series forecasting across four ETT datasets, QFWP-ANO achieves the lowest MSE in 16 of 20 settings and second-lowest in the remaining four, surpassing ANO-based and other strong baselines. On reinforcement learning tasks, QFWP-ANO consistently surpasses ANO-VQCs. Our results establish input-conditioned ANO as an effective approach for enhancing QNNs.
Related
- Machine Learning β-decay Half-lives and Their Application to r-Process Observables
- Machine-learning modeling of nuclear collective observables and low-lying spectra
- The Information Content of Krylov Observables: A Machine Learning Approach
- SALTED: a symmetry-adapted machine-learning program for predicting electron-densities in molecules and materials
- Machine learning for the LHC physics program: a 2025-2026 stocktake
BibTeX
@misc{lee2026learning,
title = {{Learning to Program Adaptive Non-Local Observables for Machine Learning}},
author = {Yu-Ting Lee and Samuel Yen-Chi Chen and Huan-Hsin Tseng},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.18655},
eprint = {2609.18655},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.18655},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Learning to Program Adaptive Non-Local Observables for Machine Learning
AU - Yu-Ting Lee
AU - Samuel Yen-Chi Chen
AU - Huan-Hsin Tseng
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2609.18655
UR - https://arxiv.org/abs/2609.18655
AB - Quantum neural networks (QNNs) are typically built from variational quantum circuits (VQCs), which are limited by local measurements. Adaptive non-local observables (ANO) address this by jointly optimizing circuit parameters and multi-qubit measurements. However, existing ANO-based VQCs learn only a single static observable that remains invariant across all inputs. We propose QFWP-ANO, a novel architecture which employs a classical hypernetwork to dynamically program VQC parameters and/or non-local observables conditioned on each input. On multivariate time-series forecasting across four ETT datasets, QFWP-ANO achieves the lowest MSE in 16 of 20 settings and second-lowest in the remaining four, surpassing ANO-based and other strong baselines. On reinforcement learning tasks, QFWP-ANO consistently surpasses ANO-VQCs. Our results establish input-conditioned ANO as an effective approach for enhancing QNNs.
ER -