Institute for Advanced Study(普林斯顿高等研究院);Politecnico di Milano(米兰理工大学);Tel Aviv University(特拉维夫大学);Google Research(谷歌研究院);Technion(以色列理工学院);TU Wien(维也纳工业大学)
Marco Bressan, Nataly Brukhim, Nicolo Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen
We introduce the problem of learning conditional averages in the PAC framework. The learner receives a sample labeled by an unknown target concept from a known concept class, as in standard PAC learning. However, instead of learning the target concept itself, the goal is to predict, for each instance, the average label over its neighborhood -- an arbitrary subset of points that contains the instance. In the degenerate case where all neighborhoods are singletons, the problem reduces exactly to classic PAC learning. More generally, it extends PAC learning to a setting that captures learning tasks arising in several domains, including explainability, fairness, and recommendation systems. Our main contribution is a complete characterization of when conditional averages are learnable, together with sample complexity bounds that are tight up to logarithmic factors. The characterization hinges on the joint finiteness of two novel combinatorial parameters, which depend on both the concept class and the neighborhood system, and are closely related to the independence number of the associated neighborhood graph.
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes
CWI Amsterdam(阿姆斯特丹数学与计算机科学国家研究所);Leiden University(莱顿大学);Google Research(谷歌研究院);Khoury College of Computer Sciences, Northeastern University(东北大学库里计算机科学学院)
Generalization bounds and algorithms for estimating conditional average treatment effect of dosage
Columbia University(哥伦比亚大学);Imperial College London(帝国理工学院);Babylon Health(巴比伦健康)
我们调查的任务估计的条件平均因果效应的治疗剂量对的基础系统中的因果关系的观察数据和假设的组合。这一直是流行病学或经济学等研究领域的一个长期挑战,这些领域需要治疗剂量对来做出决定,但可能无法进行随机试验来精确量化其效果和个体间的异质性。在本文中,我们扩展了(Shalit et al,2017),以在连续剂量参数的背景下给出反事实泛化误差的新界限,该参数依赖于定义反事实和分配偏差调整的不同方法。然后,该结果指导新的学习目标的定义,可以用于训练表示学习算法,对于该算法,我们在多个基准数据集上针对该问题实证地显示了新的最先进的性能结果,包括与双重鲁棒估计方法的比较。
Denoised Conformal Alignment for Reliable Selection of Conditional Average Treatment Effect Predictions
Shanghai Jiao Tong University(上海交通大学);Shanghai University of Finance and Economics(上海财经大学);National University of Defense Technology(国防科学技术大学);School of Statistics and Data Science(统计与数据科学学院);Institute of Big Data Research(大数据研究院)
Educational Effects in Mathematics: Conditional Average Treatment Effect depending on the Number of Treatments
Kogakuin University(工学院大学);Waseda University(早稻田大学);Osaka Institute of Technology(大阪工业大学);Osaka Sangyo University(大阪产业大学);International University of Health and Welfare(国际医疗福祉大学)
A Guide to Estimating Conditional Average Treatment Effects in Competing Risks Settings
Department of Statistics, TU Dortmund University(图恩-多特蒙德大学统计学系);Research Center Trustworthy Data Science and Security, University Alliance Ruhr (UA Ruhr)(鲁尔大学联盟可信数据科学与安全研究中心);Institute for Mathematics, University of Augsburg(艾希施泰特大学数学研究所)
Multi-CATE: Multi-Accurate Conditional Average Treatment Effect Estimation Robust to Unknown Covariate Shifts
Ludwig-Maximilians-University of Munich(慕尼黑大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);Cornell University(康奈尔大学);University of Southern California(南加州大学)
Estimation of conditional average treatment effects on distributed confidential data
Center for Artificial Intelligence Research(人工智能研究中心);Tsukuba Institute for Advanced Research(茨鲁巴高级研究机构);University of Tsukuba(茨鲁巴大学);Graduate School of Science and Technology(科学与技术研究生院);Faculty of Engineering, Information and Systems(工程、信息与系统学部)
针对多方机密数据难以集中的问题,提出 data collaboration double machine learning,利用隐私保护融合数据估计并检验半参数 CATE 模型,且支持跨时间、跨方协作。