发表机构
University of South Florida; Florida International University; DEVCOM Army Research Lab（南佛罗里达大学; 佛罗里达国际大学; DEVCOM陆军研究实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
DePICT通过KKT条件识别并移除不影响最优解的上下文方向，构建决策保持接口，在受控实验中显著降低预测遗憾。
AI 中文摘要
约束优化问题可能在目标函数和活动约束中包含某个参数，但最终决策可能对该参数的微小变化不敏感。这引出了一个基本问题：决策系统真正依赖哪些输入？基于此问题，我们提出了DePICT，一种通过根据优化器解敏感性对上下文方向进行排序，并在操作区间内聚合这些方向来构建决策保持接口的程序。我们在高维设置下研究该问题，其中原始上下文参数化一个约束任务，下游智能体仅观察上下文方向的选定子集。对于局部正则的约束程序，我们推导出基于Karush-Kuhn-Tucker（KKT）的刻画，以确定上下文方向何时与优化器相关。我们的分析表明，出现在活动优化问题中并不一定意味着变量影响最终决策。某些上下文方向可以改变KKT条件，但保持最优解不变，因为其效应被对偶变量吸收。DePICT正是设计用于移除这些方向。在受控诊断中，它精确恢复决策相关接口，并将线性预测器遗憾降至0.009，而最强竞争基线为0.475。
英文摘要
A constrained optimization problem may involve a parameter in its objective and active constraints, yet the final decision may remain insensitive to small changes in that parameter. This raises a fundamental question: which inputs does a decision making system truly depend on? Building on this question, we introduce DePICT, a procedure for constructing decision preserving interfaces by ranking context directions according to the optimizer's solution sensitivity and aggregating them across an operating regime. We study this problem in a high dimensional setting where primitive context parameterizes a constrained task and the downstream agent observes only a selected subset of context directions. For locally regular constrained programs, we derive a Karush Kuhn Tucker (KKT) based characterization of when a context direction is optimizer relevant. Our analysis shows that appearing in the active optimization problem does not necessarily imply that a variable affects the final decision. Some context directions can alter the KKT conditions while leaving the optimal solution unchanged because their effect is absorbed by the dual variables. DePICT is designed to remove exactly these directions. In a controlled diagnosis, it recovers the decision relevant interface exactly and reduces linear predictor regret to 0.009, compared with 0.475 for the strongest competing baseline.
