Learning to Program Adaptive Non-Local Observables for Machine Learning
This research introduces a novel architecture for quantum neural networks that improves performance on time-series forecasting and reinforcement learning tasks.
A new architecture called QFWP-ANO uses a classical hypernetwork to dynamically program VQC parameters and non-local observables based on each input.
On multivariate time-series forecasting across four ETT datasets, QFWP-ANO achieved 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 outperformed ANO-VQCs.
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.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include QFWP-ANO, Adaptive non-local observables, Quantum neural networks, time-series forecasting.
Source attribution: curated from arXiv cs.LG (@Yu-Ting Lee, Samuel Yen-Chi Chen, Huan-Hsin Tseng).