Saved in:
Bibliographic Details
Main Authors: Peng, Yifeng, Li, Dantong, Li, Xinyi, Liang, Zhiding, Ding, Yongshan, Wang, Ying
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.19307
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Kullback--Leibler (KL) divergence is a fundamental measure of the dissimilarity between two probability distributions, but it can become unstable in high-dimensional settings due to its sensitivity to mismatches in distributional support. To address robustness limitations, we propose a novel Quantum-Inspired Fidelity-based Divergence (QIF), leveraging quantum information principles yet efficiently computable on classical hardware. Compared to KL divergence, QIF demonstrates improved numerical stability under partial or near-disjoint support conditions, thereby reducing the need for extensive regularization in specific scenarios. Moreover, QIF admits well-defined theoretical bounds and continuous similarity measures. Building on this, we introduce a novel regularization method, QR-Drop, which utilizes QIF to improve generalization in machine learning models. Empirical results show that QR-Drop effectively mitigates overfitting and outperforms state-of-the-art methods.