Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects
Chalmers University of Technology（查尔姆斯理工大学）；Technion, Israel Institute of Technology（以色列理工学院）；Cornell Tech（康奈尔理工学院）；Massachusetts Institute of Technology（麻省理工学院）
Fredrik D. Johansson, Uri Shalit, Nathan Kallus, David Sontag
Practitioners in diverse fields such as healthcare, economics and education are eager to apply machine learning to improve decision making. The cost and impracticality of performing experiments and a recent monumental increase in electronic record keeping has brought attention to the problem of evaluating decisions based on non-experimental observational data. This is the setting of this work. In particular, we study estimation of individual-level causal effects, such as a single patient's response to alternative medication, from recorded contexts, decisions and outcomes. We give generalization bounds on the error in estimated effects based on distance measures between groups receiving different treatments, allowing for sample re-weighting. We provide conditions under which our bound is tight and show how it relates to results for unsupervised domain adaptation. Led by our theoretical results, we devise representation learning algorithms that minimize our bound, by regularizing the representation's induced treatment group distance, and encourage sharing of information between treatment groups. We extend these algorithms to simultaneously learn a weighted representation to further reduce treatment group distances. Finally, an experimental evaluation on real and synthetic data shows the value of our proposed representation architecture and regularization scheme.
Causal machine learning for predicting treatment outcomes
LMU Munich（慕尼黑大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；University of Cambridge（剑桥大学）；TU Munich（慕尼黑工业大学）；Helmholtz Munich（慕尼黑亥姆霍兹中心）；Harvard Medical School（哈佛医学院）；Cambridge Centre for AI in Medicine（剑桥人工智能医学中心）；The Alan Turing Institute（阿兰·图灵研究所）
Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data
Department of Economics, Northeastern University（东北大学经济学系）；Center for Health Policy and Healthcare Research, Northeastern University（东北大学健康政策与医疗研究中心）；Department of Public Health and Health Sciences, Bouvé College of Health Sciences, Northeastern University（东北大学布维健康科学学院公共卫生与健康科学系）
Institute of Medical Technology, Peking University Health Science Center（北京大学人民医院医学技术研究所）；National Institute of Health Data Science (NIHDS), Peking University（北京大学国家健康数据科学研究院）；Chalmers University of Technology（挑战大学）；NIHDS, Peking University（北京大学国家健康数据科学研究院）；Visualization Research Center (VISUS), University of Stuttgart（斯图加特大学可视化研究中心）；iDV x Lab, Tongji University（同济大学iDV x实验室）；National Institute of Traditional Chinese Medicine Constitution and Preventive Treatment of Diseases, Beijing University of Chinese Medicine（北京中医药大学国家中医体质与疾病预防治疗研究所）
On Learning Necessary and Sufficient Causal Graphs
University of California, Irvine（加州大学尔湾分校）；University of Michigan（密歇根大学）；University of California, Berkeley（加州大学伯克利分校）；North Carolina State University（北卡罗来纳州立大学）
Causally-informed Deep Learning towards Explainable and Generalizable Outcomes Prediction in Critical Care
Tsinghua University（清华大学）；Institute of Brain and Cognitive Sciences, Tsinghua University（清华大学脑与认知科学研究院）；Chinese PLA General Hospital（中国人民解放军总医院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Causal Invariance Learning via Efficient Nonconvex Optimization
Department of Statistics, Rutgers University（罗格斯大学统计系）；Seminar for Statistics, ETH Zürich（苏黎世联邦理工学院统计研究所）；Center for Data Science, Zhejiang University（浙江大学数据科学中心）
Explaining Outcomes of Multi-Party Dialogues using Causal Learning
Tata Consultancy Services Limited（塔塔咨询服务有限公司）；Indian Institute of Technology Kharagpur（印度理工学院卡哈拉格普尔分校）；Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）
Kernel-based estimators for functional causal effects
School of Mathematical Sciences, Horizon Digital Economy Institute, University of Nottingham, Nottingham, UK（数学科学学院，Horizon数字经济研究所，诺丁汉大学，诺丁汉，英国）；Department of Statistics, Rice University, USA（统计学系，里士满大学，美国；伯克利国家实验室，美国）；Lawrence Berkeley National Laboratory, USA（统计科学组，洛斯阿拉莫斯国家实验室，美国）；Statistical Sciences Group, Los Alamos National Laboratory, USA（数学科学学院，诺丁汉大学，诺丁汉，英国）；School of Mathematical Sciences, University of Nottingham, Nottingham, UK
