arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.16644cs.LG
收藏

在时间非平稳性下学习可部署的因果作用几何

Learning Deployable Causal Action Geometry under Temporal Non-Stationarity

Peking University(北京大学);Taobao & Tmall Group of Alibaba(阿里巴巴淘宝天猫集团);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))

Changjian Liu, Tianyu Wang, Yuwei Xu, Xiaoxuan Deng, Zhilin Zhang, Yong Gao, Chuan Yu, Jian Xu, Bo Zheng

AI总结:

针对时间非平稳性下连续决策响应规律的泛化难题,提出可部署的因果作用几何,开发两阶段正交估计器,经实验验证其在淘宝 A/B 测试中可提升 GMV 与购买量

摘要:

从观测时间序列学习连续决策的响应规律是许多现实决策系统的核心,但时间非平稳性带来了根本挑战:随着结果随时间漂移,朴素池化模型会将作用效应与变化的基线混淆,甚至反转作用排名。即使单步响应可识别,无约束的跨时间泛化仍根本不适定。因此,我们寻求即使在结果水平变化时仍对决策保持稳定的响应部分。我们提出可部署的因果作用几何:在选定链接尺度上消除与作用无关的水平偏移并剔除正幅度变化后保留的作用-响应形状。基于该目标,我们开发了两阶段正交估计器,首先获得锚定响应的交叉拟合试点估计,然后对链接、表示和形状类进行诚实的轮廓选择。所得估计器对受限目标具有 oracle 保证,且在近似持续性下,生成的决策规则在未来时期仍接近最优。在合成数据和 Dominick's 数据集上的实验验证了所提目标及其迁移行为;在随机淘宝 A/B 测试中,部署的系统使 GMV 和购买量分别提升了 1.16% 和 1.70%。

英文摘要:

Learning a response law for continuous decisions from observational time series is central to many real-world decision systems, yet temporal non-stationarity poses a fundamental challenge: as outcomes drift over time, naively pooled models can conflate action effects with shifting baselines and even reverse action rankings. Even when the one-step response is identifiable, unrestricted cross-time generalization remains fundamentally ill-posed. We therefore seek the part of the response that remains stable for decisions even when outcome levels do not. We propose deployable causal action geometry: the action-response shape that remains after anchoring away action-independent level shifts on a selected link scale and profiling out positive amplitude variation. Building on this target, we develop a two-stage orthogonal estimator that first obtains cross-fitted pilot estimates of anchored responses and then performs honest profiled selection over link, representation, and shape classes. The resulting estimator admits oracle guarantees for the restricted target and, under approximate persistence, produces decision rules that remain near optimal in future periods. Experiments on synthetic data and Dominick's support the proposed target and its transfer behavior. In a randomized Taobao A/B test, the deployed system improves GMV and purchase counts by \(1.16\%\) and \(1.70\%\).

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。

↑