论文标题
在监督量子机学习模型中发现自动特征空间发现的增强方法
Boosting Method for Automated Feature Space Discovery in Supervised Quantum Machine Learning Models
论文作者
论文摘要
量子支持向量机（QSVM）已成为量子内核方法研究和应用中的重要工具。在这项工作中，我们提出了一种促进QSVM模型组合的方法，并评估多个数据集的性能改进。这种方法源自在传统机器学习中效果很好的最佳合奏建筑实践，因此应该进一步推动量子模型性能的限制。我们发现，在某些情况下，带有调谐超参数的单个QSVM模型足以模拟数据，而在其他情况下 - 通过建议的方法被迫通过被迫通过被迫对特征空间进行探索的QSVM集合是有益的。
Quantum Support Vector Machines (QSVM) have become an important tool in research and applications of quantum kernel methods. In this work we propose a boosting approach for building ensembles of QSVM models and assess performance improvement across multiple datasets. This approach is derived from the best ensemble building practices that worked well in traditional machine learning and thus should push the limits of quantum model performance even further. We find that in some cases, a single QSVM model with tuned hyperparameters is sufficient to simulate the data, while in others - an ensemble of QSVMs that are forced to do exploration of the feature space via proposed method is beneficial.
