Scalable Neural Wave Functions via Information Mixing and Hierarchical Network Architectures
Abstract
Numerically simulating quantum many-body systems is one of the central challenges in modern physics, as the exponential growth of the Hilbert space with system size renders large-scale exact solutions intractable. Over the past decade, generative artificial neural networks have emerged as powerful wave function ansätze that have powered advances in finding ground state representations, reconstructing quantum states from data, and modeling dynamics in quantum many-body systems. While recurrent neural networks (RNNs) are computationally efficient, the recurrent nature can limit their capacity to capture long-range correlations. Transformer models with their underlying self-attention mechanism excel at capturing these long-range correlations, but incur increased computational requirements, restricting applications to small physical systems. In this work, we address these limitations by exploring the multi-layer perceptron (MLP) mixer model as a wave function ansatz. By mixing information globally and locally through the system via a computationally lightweight mixing strategy, this architecture promises to combine the ability to capture long-range correlations with low computational costs. We benchmark the model on finding ground state representations of two-dimensional quantum many-body systems in various phases of matter and investigate the behavior of representational accuracy and computational efficiency for different physical system sizes. By comparing its performance to RNNs and transformer models with single-site and patched input definitions, we demonstrate that the MLP mixer architecture performs competitively with state-of-the-art network models. We further show that a hierarchical combination of this model with the transformer model outperforms other state-of-the-art architectures for large-scale quantum systems, opening new avenues for investigating quantum phases of matter.
Related
- Neural network–augmented Pfaffian wave-functions for scalable simulations of interacting fermions
- Scalable Multiple Electron Transport Architectures for Feedback Traceable Current Sources
- Scalable Transpilation for Overcoming Restricted Connectivity in Distributed Superconducting Quantum Architectures
- Self-regulated emergence of heavy-tailed weight distributions in evolving complex network architectures
- A scalable estimator of higher-order information in complex dynamical systems
BibTeX
@misc{oyedemi2026scalable,
title = {{Scalable Neural Wave Functions via Information Mixing and Hierarchical Network Architectures}},
author = {Faith Oyedemi and Stefanie Czischek},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.30257},
eprint = {2610.30257},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.30257},
}
RIS
TY - UNPB
TI - Scalable Neural Wave Functions via Information Mixing and Hierarchical Network Architectures
AU - Faith Oyedemi
AU - Stefanie Czischek
PY - 2026
DA - 2026/10/21
PB - arXiv
DO - 10.48550/arxiv.2610.30257
UR - https://arxiv.org/abs/2610.30257
AB - Numerically simulating quantum many-body systems is one of the central challenges in modern physics, as the exponential growth of the Hilbert space with system size renders large-scale exact solutions intractable. Over the past decade, generative artificial neural networks have emerged as powerful wave function ansätze that have powered advances in finding ground state representations, reconstructing quantum states from data, and modeling dynamics in quantum many-body systems. While recurrent neural networks (RNNs) are computationally efficient, the recurrent nature can limit their capacity to capture long-range correlations. Transformer models with their underlying self-attention mechanism excel at capturing these long-range correlations, but incur increased computational requirements, restricting applications to small physical systems. In this work, we address these limitations by exploring the multi-layer perceptron (MLP) mixer model as a wave function ansatz. By mixing information globally and locally through the system via a computationally lightweight mixing strategy, this architecture promises to combine the ability to capture long-range correlations with low computational costs. We benchmark the model on finding ground state representations of two-dimensional quantum many-body systems in various phases of matter and investigate the behavior of representational accuracy and computational efficiency for different physical system sizes. By comparing its performance to RNNs and transformer models with single-site and patched input definitions, we demonstrate that the MLP mixer architecture performs competitively with state-of-the-art network models. We further show that a hierarchical combination of this model with the transformer model outperforms other state-of-the-art architectures for large-scale quantum systems, opening new avenues for investigating quantum phases of matter.
ER -