Quantum-Inspired Spectral Geometry for Neural Operator Equivalence and Structured Pruning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shao, Haijian, Liu, Wei, Deng, Xing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917114561953792
author Shao, Haijian
Liu, Wei
Deng, Xing
author_facet Shao, Haijian
Liu, Wei
Deng, Xing
contents The rapid growth of multimodal intelligence on resource-constrained and heterogeneous domestic hardware exposes critical bottlenecks: multimodal feature heterogeneity, real-time requirements in dynamic scenarios, and hardware-specific operator redundancy. This work introduces a quantum-inspired geometric framework for neural operators that represents each operator by its normalized singular value spectrum on the Bloch hypersphere. We prove a tight spectral-to-functional equivalence theorem showing that vanishing Fubini--Study/Wasserstein-2 distance implies provable functional closeness, establishing the first rigorous foundation for cross-modal and cross-architecture operator substitutability. Based on this metric, we propose Quantum Metric-Driven Functional Redundancy Graphs (QM-FRG) and one-shot structured pruning. Controlled simulation validates the superiority of the proposed metric over magnitude and random baselines. An extensive experimental validation on large-scale multimodal transformers and domestic heterogeneous hardware (Huawei Ascend, Cambricon MLU, Kunlunxin) hardware is deferred to an extended journal version currently in preparation.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00880
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantum-Inspired Spectral Geometry for Neural Operator Equivalence and Structured Pruning
Shao, Haijian
Liu, Wei
Deng, Xing
Computer Vision and Pattern Recognition
The rapid growth of multimodal intelligence on resource-constrained and heterogeneous domestic hardware exposes critical bottlenecks: multimodal feature heterogeneity, real-time requirements in dynamic scenarios, and hardware-specific operator redundancy. This work introduces a quantum-inspired geometric framework for neural operators that represents each operator by its normalized singular value spectrum on the Bloch hypersphere. We prove a tight spectral-to-functional equivalence theorem showing that vanishing Fubini--Study/Wasserstein-2 distance implies provable functional closeness, establishing the first rigorous foundation for cross-modal and cross-architecture operator substitutability. Based on this metric, we propose Quantum Metric-Driven Functional Redundancy Graphs (QM-FRG) and one-shot structured pruning. Controlled simulation validates the superiority of the proposed metric over magnitude and random baselines. An extensive experimental validation on large-scale multimodal transformers and domestic heterogeneous hardware (Huawei Ascend, Cambricon MLU, Kunlunxin) hardware is deferred to an extended journal version currently in preparation.
title Quantum-Inspired Spectral Geometry for Neural Operator Equivalence and Structured Pruning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.00880