Electronic excitation spectra and recovery of excited states with neural network wave functions
Abstract
Accurate electronic spectra require both a flexible description of electron correlation and a tractable treatment of the many states contributing to the response. We combine neural network wave functions with the Lorentz integral transform to calculate electronic spectra directly in continuous coordinates, without truncation error from a fixed one-electron basis and with polynomial computational cost per optimization step. Instead of constructing a prescribed set of excited states, the method solves an inhomogeneous Schrödinger equation at a chosen complex energy. This formulation gives access, in principle, to the entire spectrum coupled to a perturbation, including bound excitations and the ionization continuum, without explicitly determining all lower-lying eigenstates. A finite imaginary energy controls the resolution and keeps the response square integrable. Near an isolated bound excitation, the normalized response also recovers the corresponding eigenstate as the width tends to zero. A helium application illustrates the extraction of an excitation energy and oscillator strength. The formulation provides a route from neural descriptions of electronic correlation to spectra beyond a small manifold of low-lying states.
Related
- Excited-state Properties Beyond the Excitation Energy from Orbital-Optimized Density Functional Calculations II: Absorption Spectra
- Unexpected Shortening of the Excited State Lifetime of Oxybenzone Radical Cation upon Excitation of the Band Origin
- Excitation-Energy Accuracy Does Not Guarantee Observable Fidelity: Rethinking Validation of Excited-State Quantum Algorithms
- Excited-state Properties Beyond the Excitation Energy from Orbital-Optimized Density Functional Calculations I: Dipole Moments of Rydberg States
- Ab Initio Investigation of Excited States and Absorption Spectra of Small Mercury Clusters (Hg2−5)
BibTeX
@misc{zhang2026electronic,
title = {{Electronic excitation spectra and recovery of excited states with neural network wave functions}},
author = {Xiaoyu Zhang and Weizhong Fu and Yixiao Chen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.36699},
eprint = {2609.36699},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.36699},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Electronic excitation spectra and recovery of excited states with neural network wave functions
AU - Xiaoyu Zhang
AU - Weizhong Fu
AU - Yixiao Chen
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.36699
UR - https://arxiv.org/abs/2609.36699
AB - Accurate electronic spectra require both a flexible description of electron correlation and a tractable treatment of the many states contributing to the response. We combine neural network wave functions with the Lorentz integral transform to calculate electronic spectra directly in continuous coordinates, without truncation error from a fixed one-electron basis and with polynomial computational cost per optimization step. Instead of constructing a prescribed set of excited states, the method solves an inhomogeneous Schrödinger equation at a chosen complex energy. This formulation gives access, in principle, to the entire spectrum coupled to a perturbation, including bound excitations and the ionization continuum, without explicitly determining all lower-lying eigenstates. A finite imaginary energy controls the resolution and keeps the response square integrable. Near an isolated bound excitation, the normalized response also recovers the corresponding eigenstate as the width tends to zero. A helium application illustrates the extraction of an excitation energy and oscillator strength. The formulation provides a route from neural descriptions of electronic correlation to spectra beyond a small manifold of low-lying states.
ER -