Saved in:
Bibliographic Details
Main Authors: Lu, Yiming, Bharadwaj, Sriram, Rathore, Dikshant, Luo, Di
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.23468
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918407093354496
author Lu, Yiming
Bharadwaj, Sriram
Rathore, Dikshant
Luo, Di
author_facet Lu, Yiming
Bharadwaj, Sriram
Rathore, Dikshant
Luo, Di
contents We establish an information-theoretic scaling law for generic autoregressive neural quantum states, determined by the middle-cut mutual information of the wavefunction amplitude. By formalizing the virtual bond as an effective information channel across a sequence bipartition, we rigorously prove that exact autoregressive representation of a quantum state requires the virtual-bond dimension to scale with the amplitude mutual information. For stabilizer-state families, we show that this law yields an explicit, analytical rank formula. Applying this framework across quantum-state tomography, ground-state and finite-temperature learning, our numerical experiments expose precise exponent matching, architecture-dependent scaling differences between recurrent and Transformer neural quantum state, and the critical role of autoregressive basis ordering. These results establish a rigorous physical link between the intrinsic structure of a quantum many-body state and the corresponding neural-network capacity required for its faithful representation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_23468
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Information-Theoretic Scaling Laws of Neural Quantum States
Lu, Yiming
Bharadwaj, Sriram
Rathore, Dikshant
Luo, Di
Quantum Physics
We establish an information-theoretic scaling law for generic autoregressive neural quantum states, determined by the middle-cut mutual information of the wavefunction amplitude. By formalizing the virtual bond as an effective information channel across a sequence bipartition, we rigorously prove that exact autoregressive representation of a quantum state requires the virtual-bond dimension to scale with the amplitude mutual information. For stabilizer-state families, we show that this law yields an explicit, analytical rank formula. Applying this framework across quantum-state tomography, ground-state and finite-temperature learning, our numerical experiments expose precise exponent matching, architecture-dependent scaling differences between recurrent and Transformer neural quantum state, and the critical role of autoregressive basis ordering. These results establish a rigorous physical link between the intrinsic structure of a quantum many-body state and the corresponding neural-network capacity required for its faithful representation.
title Information-Theoretic Scaling Laws of Neural Quantum States
topic Quantum Physics
url https://arxiv.org/abs/2603.23468