Saved in:
Bibliographic Details
Main Authors: Zendejas-Morales, Claudia, Saikia, Debashis, Singh, Utkarsh
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.16097
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915803813642240
author Zendejas-Morales, Claudia
Saikia, Debashis
Singh, Utkarsh
author_facet Zendejas-Morales, Claudia
Saikia, Debashis
Singh, Utkarsh
contents Fidelity-based quantum kernels provide a direct interface between quantum feature maps and classical kernel methods, but they can exhibit exponential concentration: with increasing system size or circuit expressivity, the Gram matrix approaches the identity and suppresses informative similarity structure. We present an empirical study of two mitigation strategies implemented in Qiskit: (i) local (patch-wise) kernels that aggregate subsystem similarities, and (ii) multi-scale kernels that mix local and global similarity across patch granularities. We benchmark baseline, local, and multi-scale kernels under matched preprocessing, splits, and SVM protocols on several tabular datasets, sweeping the feature dimension $d\in\{4,6,\dots,20\}$. We report concentration diagnostics based on off-diagonal kernel statistics, spectral richness via effective rank, and centered alignment with labels. Across datasets, local and multi-scale constructions consistently mitigate concentration and yield richer kernel spectra relative to the global fidelity baseline, while the impact on classification accuracy depends on the dataset and dimension.
format Preprint
id arxiv_https___arxiv_org_abs_2602_16097
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Local and Multi-Scale Strategies to Mitigate Exponential Concentration in Quantum Kernels
Zendejas-Morales, Claudia
Saikia, Debashis
Singh, Utkarsh
Quantum Physics
Fidelity-based quantum kernels provide a direct interface between quantum feature maps and classical kernel methods, but they can exhibit exponential concentration: with increasing system size or circuit expressivity, the Gram matrix approaches the identity and suppresses informative similarity structure. We present an empirical study of two mitigation strategies implemented in Qiskit: (i) local (patch-wise) kernels that aggregate subsystem similarities, and (ii) multi-scale kernels that mix local and global similarity across patch granularities. We benchmark baseline, local, and multi-scale kernels under matched preprocessing, splits, and SVM protocols on several tabular datasets, sweeping the feature dimension $d\in\{4,6,\dots,20\}$. We report concentration diagnostics based on off-diagonal kernel statistics, spectral richness via effective rank, and centered alignment with labels. Across datasets, local and multi-scale constructions consistently mitigate concentration and yield richer kernel spectra relative to the global fidelity baseline, while the impact on classification accuracy depends on the dataset and dimension.
title Local and Multi-Scale Strategies to Mitigate Exponential Concentration in Quantum Kernels
topic Quantum Physics
url https://arxiv.org/abs/2602.16097