Optimizing Detection Time and Specificity: Early Classification of Time Series with Sensitivity Constraint

Jiaming Qiu, Ying-Qi Zhao, Yingye ZhengBDU @ NeurIPS 2024 · OpenReview

Abstract

From the perspective of sequential decision making, we propose a novel approach for early classification of time series under the Neyman--Pearson paradigm that incorporates a sensitivity constraint. We explicitly formulate the optimal solution, which can be practically obtained utilizing plug-in estimators such as recurrent neural networks. Cast as a constrained multi-objective optimization problem, we establish the Pareto optimality balancing earliness and classification accuracy. Our approach visualizes the inherent trade-off between earliness and specificity, ensuring informed decision making without compromising sensitivity. Experimental validation confirms the feasibility of our approach, demonstrating its potential in various real-world applications.
BibTeX
@inproceedings{qiu2024optimizing,
  author = {Jiaming Qiu and Ying-Qi Zhao and Yingye Zheng},
  title = {{Optimizing Detection Time and Specificity: Early Classification of Time Series with Sensitivity Constraint}},
  booktitle = {BDU @ NeurIPS},
  year = {2024},
  url = {https://openreview.net/forum?id=PXVqsZlxEa},
}

Loading related content...

Figure