将经典不确定性量化方法迁移到量子机器学习，提升模型透明度。
Old Rules in a New Game: Mapping Uncertainty Quantification to Quantum Machine Learning
- 基于经典不确定性方法构建量子领域适用的量化框架
- 实验证明经典思路可有效增强量子模型的可信度
- 适合关注量子模型可靠性与可解释性的研究者
传统深度学习因模型结构日益复杂导致透明度下降，引发过拟合与预测过度自信等问题。随着量子机器学习在计算能力与潜在空间复杂性上的潜力显现，其同样面临黑箱行为难题。尽管经典领域已有大量不确定性量化研究，但量子机器学习仍缺乏相应进展。本文通过借鉴经典不确定性量化成果及早期量子贝叶斯建模探索，理论推导并实证评估了将经典方法映射至量子机器学习领域的技术路径。结果表明，融合经典不确定性认知对于设计具备感知能力的新一代量子机器学习模型至关重要。
原文摘要 · Abstract (English)
One of the key obstacles in traditional deep learning is the reduction in model transparency caused by increasingly intricate model functions, which can lead to problems such as overfitting and excessive confidence in predictions. With the advent of quantum machine learning offering possible advances in computational power and latent space complexity, we notice the same opaque behavior. Despite significant research in classical contexts, there has been little advancement in addressing the black-box nature of quantum machine learning. Consequently, we approach this gap by building upon existing work in classical uncertainty quantification and initial explorations in quantum Bayesian modeling to theoretically develop and empirically evaluate techniques to map classical uncertainty quantification methods to the quantum machine learning domain. Our findings emphasize the necessity of leveraging classical insights into uncertainty quantification to include uncertainty awareness in the process of designing new quantum machine learning models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。