再学习的代价：动态决策中的歧义溯源
The Price of Relearning: Ambiguity Provenance in Dynamic Decisions
浏览论文内容
中文总结 AI 辅助
该研究针对动态决策中再学习改变评估者的问题，提出保溯源构造子与三角 vintage 表示，明确再学习代价的定义，分析其计算复杂度并给出校准方法。
中文摘要 AI 辅助
动态鲁棒系统会随数据到来重建歧义集。新集不必是支撑先前行动的模型的贝叶斯延续：再学习可改变评估者，而非仅改变估计值。在连续紧值类中，似然商刻画了保溯源构造子。当溯源失效时，无选择的三角 vintage 表示是精确的，其定向福利缺口定义了再学习的代价。端点与记忆结果表明为何 vintage 状态通常必要，以及何时可实现相干压缩。明确列出单步歧义律的指定有限模型仍可多项式评估，而通用认证是 NP 难的。兼容设计提供了修复方案，条件短视定价基准展现了行动-信息-歧义反馈；扫描证据校准其规模，无需被解读为因果协议实验。
英文摘要
Dynamic robust systems often rebuild ambiguity sets as data arrive. Relearning can then replace the evaluator rather than merely update its beliefs; we call this dependence on an uncertainty set's date of origin ambiguity provenance. Under weak-evidence richness, a likelihood quotient exactly characterizes continuous compact-valued reconstruction rules that preserve Bayesian provenance. When compatibility fails and the discrepancy is decision-visible, sophisticated behavior admits an exact triangular evaluator-vintage representation before operationally redundant vintages are quotiented out. The directed welfare loss from later reconstruction is the Price of Relearning. We characterize when vintage state can be compressed, the divide between polynomial evaluation of specified finite models and NP-hard universal certification, and a compatible reconstruction that repairs the protocol. A Gaussian pricing benchmark closes the reconstruction-action-information loop; scanner data calibrate its scale without a causal protocol claim.
