Saved in:
Bibliographic Details
Main Authors: Lin, Yu-Cheng, Hsu, Yu-Chao, Tsai, I-Shan, Lin, Chun-Hua, Peng, Kuo-Chung, Jiang, Jiun-Cheng, Wang, Yun-Yuan, Huang, Tzung-Chi, Li, Tai-Yue, Chen, Kuan-Cheng, Chen, Samuel Yen-Chi, Chen, Nan-Yow
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.04604
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917463589912576
author Lin, Yu-Cheng
Hsu, Yu-Chao
Tsai, I-Shan
Lin, Chun-Hua
Peng, Kuo-Chung
Jiang, Jiun-Cheng
Wang, Yun-Yuan
Huang, Tzung-Chi
Li, Tai-Yue
Chen, Kuan-Cheng
Chen, Samuel Yen-Chi
Chen, Nan-Yow
author_facet Lin, Yu-Cheng
Hsu, Yu-Chao
Tsai, I-Shan
Lin, Chun-Hua
Peng, Kuo-Chung
Jiang, Jiun-Cheng
Wang, Yun-Yuan
Huang, Tzung-Chi
Li, Tai-Yue
Chen, Kuan-Cheng
Chen, Samuel Yen-Chi
Chen, Nan-Yow
contents High-performance computing (HPC) is increasingly important for scalable quantum chemistry workflows that couple classical generative models, quantum circuit simulation, and selected configuration interaction postprocessing. We present the generative quantum-inspired Kolmogorov-Arnold eigensolver (GQKAE), a parameter-efficient extension of the generative quantum eigensolver (GQE) for quantum chemistry. GQKAE replaces the parameter-heavy feed-forward network components in GPT-style generative eigensolvers with hybrid quantum-inspired Kolmogorov-Arnold network modules, forming a compact HQKANsformer backbone. The method preserves autoregressive operator selection and the quantum-selected configuration interaction evaluation pipeline, while using single-qubit DatA Re-Uploading ActivatioN modules to provide expressive nonlinear mappings. Numerical benchmarks on H4, N2, LiH, C2H6, H2O, and the H2O dimer show that GQKAE achieves chemical accuracy comparable to the GPT-based GQE architecture, while reducing trainable parameters and memory by approximately 66% and improving wall-time performance. For strongly correlated systems such as N2 and LiH, GQKAE also improves convergence behavior and final energy errors. These results indicate that quantum-inspired Kolmogorov-Arnold networks can reduce classical-side overhead while preserving circuit-generation quality, offering a scalable route for HPC-quantum co-design on near-term quantum platforms.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04604
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generative Quantum-inspired Kolmogorov-Arnold Eigensolver
Lin, Yu-Cheng
Hsu, Yu-Chao
Tsai, I-Shan
Lin, Chun-Hua
Peng, Kuo-Chung
Jiang, Jiun-Cheng
Wang, Yun-Yuan
Huang, Tzung-Chi
Li, Tai-Yue
Chen, Kuan-Cheng
Chen, Samuel Yen-Chi
Chen, Nan-Yow
Quantum Physics
Machine Learning
High-performance computing (HPC) is increasingly important for scalable quantum chemistry workflows that couple classical generative models, quantum circuit simulation, and selected configuration interaction postprocessing. We present the generative quantum-inspired Kolmogorov-Arnold eigensolver (GQKAE), a parameter-efficient extension of the generative quantum eigensolver (GQE) for quantum chemistry. GQKAE replaces the parameter-heavy feed-forward network components in GPT-style generative eigensolvers with hybrid quantum-inspired Kolmogorov-Arnold network modules, forming a compact HQKANsformer backbone. The method preserves autoregressive operator selection and the quantum-selected configuration interaction evaluation pipeline, while using single-qubit DatA Re-Uploading ActivatioN modules to provide expressive nonlinear mappings. Numerical benchmarks on H4, N2, LiH, C2H6, H2O, and the H2O dimer show that GQKAE achieves chemical accuracy comparable to the GPT-based GQE architecture, while reducing trainable parameters and memory by approximately 66% and improving wall-time performance. For strongly correlated systems such as N2 and LiH, GQKAE also improves convergence behavior and final energy errors. These results indicate that quantum-inspired Kolmogorov-Arnold networks can reduce classical-side overhead while preserving circuit-generation quality, offering a scalable route for HPC-quantum co-design on near-term quantum platforms.
title Generative Quantum-inspired Kolmogorov-Arnold Eigensolver
topic Quantum Physics
Machine Learning
url https://arxiv.org/abs/2605.04604