公平法院时间表的端到端优化与学习
摘要
美国各地的刑事法院每年要处理数百万件案件，案件时间表的安排必须容纳多样化的约束，包括法院、检察官和辩方人员的偏好和可用性。当刑事法院时间表被建立时，被告的安排偏好通常获得最低优先级，尽管被告因缺席可能面临重大后果（包括逮捕或监禁）。此外，研究表明，被告的缺席会对法院及其他系统利益相关方造成成本。为了解决这些问题，法院和评论人开始认识到，关注法院过程（包括"法院时间表实践"）会改善被告及系统的预审结果。因此，迫切需要一种公平的刑事法院预审时间表系统，能够考虑被告的偏好和可用性，但收集此类数据面临日志istical 挑战。此外，even when such data is available, optimizing schedules fairly across various parties' preferences is a complex optimization problem. In an effort to construct such a fair scheduling system under data uncertainty, this paper proposes a joint optimization and learning framework that combines machine learning models trained end-to-end with efficient matching algorithms. This framework aims to produce court scheduling schedules that optimize a principled measure of fairness, balancing the availability and preferences of all parties.
引用
@article{arxiv.2410.17415,
title = {End-to-End Optimization and Learning of Fair Court Schedules},
author = {My H Dinh and James Kotary and Lauryn P. Gouldin and William Yeoh and Ferdinando Fioretto},
journal= {arXiv preprint arXiv:2410.17415},
year = {2024}
}