非平稳下CDF的时间一致置信带
Time-uniform confidence bands for the CDF under nonstationarity
摘要：
对随机变量的完全分布的估计对于人工和自动决策都是有用的原始数据。这一问题在i.i.d.得到了广泛的关注。设置，但任意的数据依赖设置仍然在很大程度上未得到解决。与已知的不可能性结果相一致，我们提出了计算上恰当的时间一致和值一致的边界上的CDF的运行平均条件分布的实值随机变量，这总是有效的，有时平凡的，随着实例相关的收敛保证。重要性加权扩展适用于估计给定受控实验数据用尽的奖励的完全反事实分布，例如，从A/B测试或上下文强盗。
英文摘要：
Estimation of the complete distribution of a random variable is a useful primitive for both manual and automated decision making. This problem has received extensive attention in the i.i.d. setting, but the arbitrary data dependent setting remains largely unaddressed. Consistent with known impossibility results, we present computationally felicitous time-uniform and value-uniform bounds on the CDF of the running averaged conditional distribution of a real-valued random variable which are always valid and sometimes trivial, along with an instance-dependent convergence guarantee. The importance-weighted extension is appropriate for estimating complete counterfactual distributions of rewards given controlled experimentation data exhaust, e.g., from an A/B test or a contextual bandit.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
