Peter Spirtes
个人简介
Peter Spirtes是卡内基梅隆大学的Marianna Brown Dietrich教授和哲学系主任。他的研究兴趣跨越多个基础学科,涉及哲学、统计学、图论和计算机科学。他的研究对一些需要从统计数据中进行因果推断的学科有着深刻的影响。
Peter Spirtes与Clark Glymour一起提出了最早的因果发现算法之一,即PC。他还发表了该领域广泛使用的参考书之一("Causation, Prediction, and Search[1]")。他的工作表明,在某些情况下,有一些计算机程序可以在合理的假设下从实验或非实验数据,或两者的组合中,可靠地得出有用的因果结论。他目前的研究集中如何将因果科学的基础假设弱化,从而将结果的应用扩展到更广泛,更通用的场景中。同时,他也关注因果发现在大规模数据上的引用。
Peter Spirtes的研究对包括生物学在内的许多不同学科都有重要的理论和实践意义。在理论上,它帮助我们理解了概率和因果关系之间的关系,以及在各种不同的假设下,从各种数据中进行可靠的因果推断的确切限度是什么。在实践上,它为科学家提供了一个有用的工具,帮助他们建立因果模型。
研究成果
许多流行病学、计量经济学、社会学和政治学都试图利用在不可能进行完全控制实验的情况下收集的数据来推断因果关系。
Peter Spirtes目前研究的目标(称为 TETRAD 项目)可以分为两个主要部分。第一个目标是具体说明并证明在什么条件下可以从未在完全受控条件下获得的背景知识和统计数据可靠地推断出因果关系。第二个目标是开发、分析、实施、测试和应用实用的、可证明正确的计算机程序,在可能的情况下推断因果结构。这项研究的结果可在 TETRAD II 计算机程序中找到。
代表工作
Spirtes, P., Zhang, J. (forthcoming) “A Uniformly Consistent Estimator of Causal Effects Under The k-Triangle-Faithfulness Assumption”, Statistical Science.
Spirtes, P., (2013) "Calculation of Entailed Rank Constraints in Partially Non-Linear and Cyclic Models", Proceedings of the Twenty-Ninth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-13), AUAI Press, 2013, pp. 606-615.
Ramsey, J., Spirtes, P, and Glymour, C. (2011) “On meta-analyses of imaging data and the mixture of records.” NeuroImage 57(2): 323-330.
Zhang, J., and Spirtes, P. (2011) "Intervention, Determinism, and the Causal Minimality Condition”, Synthese, 2011, 182:13, pp. 335-347.
Ali, A., Richardson, T., Spirtes, P. (2009) “Markov Equivalence For Ancestral Graphs”, Annals of Statistics, 37, 5B, 2808-2837.
Tillman, R., Gretton, A. and Spirtes, P. (2009) “Nonlinear directed acyclic structure learning with weakly additive noise models”, NIPS 2009.
Spirtes, P. (2009) "Variable Definition and Causal Inference", Proceedings of the 13th International Congress of Logic Methodology and Philosophy of Science, pp. 514-53.
Zhang, J., and Spirtes, P. (2009) "Detection of Unfaithfulness and Robust Causal Inference", Minds and Machines, 18:2, pp. 239-272.
Silva, R., Glymour, C., Scheines, R. and Spirtes, P. (2006) “Learning the Structure of Latent Linear Structure Models,” Journal of Machine Learning Research, 7, 191-246.
Ramsey, J., Zhang, J., and Spirtes, P., (2006) “Adjacency-Faithfulness and Conservative Causal Inference”, Uncertainty in Artificial Intelligence 2006, Boston, MA.
Spirtes, P. (2005) “Graphical Models, Causal Inference, and Econometric Models”, Journal of Economic Methodology. 2005 12:1, pp. 1–33.
Zhang, J., and Spirtes, P. (2005) “A Transformational Characterization of Markov Equivalence for Directed Acyclic Graphs with Latent Variables”, Uncertainty in Artificial Intelligence 2005, Edinboro, Scotland.
Ali, R., Richardson, T., Spirtes, P., and Zhang, J. (2005) “Towards Characterizing Markov Equivalence Classes for Directed Acyclic Graph Models with Latent Variables”, Uncertainty in Artificial Intelligence 2005, Edinboro, Scotland.
Spirtes, P., and Scheines, R. (2004). “Causal Inference of Ambiguous Manipulations”, in Proceedings of the Philosophy of Science Association Meetings, 2002.
Chu, T., Glymour, C., Scheines, R., Spirtes, P. (2003) “A Statistical Problem for Inference to Regulatory Structure from Associations of Gene Expression Measurements with Microarrays”, Bioinformatics, 19, pp. 1147-1152.
Robins, J., Scheines, R., Spirtes, P., and Wasserman, L. (2003). “Uniform Consistency in Causal Inference”, Biometrika, September, 90: pp. 491 – 515.
Zhang, J., and Spirtes, P. (2003) “Strong Faithfulness and Uniform Consistency in Causal Inference”, UAI '03, Proceedings of the 19th Conference in Uncertainty in Artificial Intelligence, August 7-10 2003, Acapulco, Mexico, ed. by Christopher Meek and Uffe Kjarulff, Morgan Kaufmann.
Richardson, T., Spirtes, P. (2002) “Ancestral Graph Markov Models”, Annals of Statistics, 2002, 30 pp. 962-1030.
Spirtes, P., Glymour, C. and Scheines, R. (2000). Causation, Prediction, and Search, 2nd ed. New York, N.Y.: MIT Press.
Spirtes, P., Glymour, C., and Scheines, R. (2000) Constructing Bayesian Network Models of Gene Expression Networks from Microarray Data, to appear in the Proceedings of the Atlantic Symposium on Computational Biology, Genome Information Systems & Technology.
Robins, J., Scheines, R., Spirtes, P., and Wasserman, L. (2000) Uniform Consistency in Causal Inference, Carnegie Mellon University Department of Statistics Technical Report 725.
Richardson, T., and Spirtes, P. (2000) Ancestral Markov Graphical Models, University of Washington Department of Statistics Technical Report 375.
Spirtes, P. (2000) An Anytime Algorithm for Causal Inference, to be presented at AI and Statistics 2001.
Spirtes, P. (1997). Limits on Causal Inference from Statistical Data, presented at American Economics Association Meeting.
Spirtes, P., Cooper, G. (1997). An Experiment in Causal Discovery Using a Pneumonia Database, Proceedings of AI and Statistics 99.
Spirtes, P., Richardson, T., Meek, C. (1997). The Dimensionality of Mixed Ancestral Graphs, Technical Report CMU-83-Phil.
Spirtes, P., Richardson, T., Meek, C., Scheines, R., and Glymour, C. (1997). Using Path Diagrams as a Structural Equation Modelling Tool, Technical Report CMU-82-Phil.
Scheines, R., Spirtes, P., Glymour, C., Meek, C., and Richardson, T. (forthcoming). The TETRAD Project: Constraint Based Aids to Causal Model Specification, Multivariate Behavioral Research
Spirtes, P., Glymour, C. and Scheines, R. (1993). Causation, Prediction, and Search, New York, N.Y.: Springer-Verlag.
Scheines, R. (forthcoming). An Introduction to Causal Inference, in Causality in Crisis, ed. by Steven Turner and Vaughan McKim, University of Notre Dame Press.
Spirtes, P., Richardson, T., Meek, C., Scheines, R., and Glymour, C., (1996). Using D-separation to Calculate Zero Partial Correlations in Linear Models with Correlated Errors, Technical Report CMU-72-Phil.
Spirtes, P., and Richardson, T. (1996). A Polynomial Time Algorithm For Determining DAG Equivalence in the Presence of Latent Variables and Selection Bias, Proceedings of the 6th International Workshop on Artificial Intelligence and Statistics.
Spirtes, P., Richardson, T., and Meek, C. (1996). Heuristic Greedy Search Algorithms for Latent Variable Models, Proceedings of the 6th International Workshop on Artificial Intelligence and Statistics.
Richardson, T., and Spirtes, P. (1996). Automated discovery of linear feedback models, Technical Report CMU-75-Phil.
Spirtes, P., and Scheines, R. (forthcoming). Reply to Freedman, in Causality in Crisis, ed. by Steven Turner and Vaughan McKim, University of Notre Dame Press.
Spirtes, P., Meek, C., and Richardson, T. (1996). Causal Inference in the Presence of Latent Variables and Selection Bias, Technical Report CMU-77-Phil.
Spirtes, P. (1995). Directed Cyclic Graphical Representation of Feedback Models, Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence, ed. by Philippe Besnard and Steve Hanks, Morgan Kaufmann Publishers, Inc., San Mateo, 1995.
编者推荐
学者相关链接
Peter SPIRTES | Professor (Full)
集智学园课程推荐
本次报告将简要示范如何使用causal-learn的因果发现python包,并使用一个开源的数据集展示数据清理和因果发现的流程细节。
本讲座将站在一种较宏观的视角对这些技术进行概述,内容将涉及但不限于:运用 Reservior 计算预测混沌、基于图网络的自动建模与控制、基于最优控制的可微分 ODE 求解技术、基于自注意力机制的人工智能统计物理学家、基于 Gumbel softmax 技术的网络重构、基于神经网络的格兰杰因果检验、基于强化学习的干预因果模型等。
主要介绍因果发现的基础背景知识,并带领大家使用Tetrad工具包,熟悉该软件的基本操作。通过实操,使参与者对结构因果模型,因果发现等概念有基础的认知。
本期分享,我们将一起阅读Elements of Causal Inference 这本书的第四章和第七章,补充因果发现领域的基础知识。探讨多变量因果模型和双变量因果模型的可识别性问题,和相应的一些经典的因果发现算法,包括但不限于多变量模型中基于约束的方法、基于打分函数的方法,双变量模型中基于加性噪声模型、信息几何(Information-Geometric Causal Inference)等方法。
本次分享会分析三种基于条件约束的算法:SGS算法、IC算法和PC算法,梳理这些算法的发展历史,比较他们的异同,分析算法的细节,并结合他们的思想设计一个因果发现算法的小实验,展示基于条件约束的因果发现发现算法的运作方法。
不同数据缺失机制下如何进行因果发现?
分享者:屠睿博 瑞典皇家工学院博士在读
在许多因果发现的许多应用领域之中,数据缺失是一个极其常见的现象。通常的处理方法是删除含有缺失数据的记录或者做简单的数据填充,然而这样做很有可能引入由数据丢失机制带来的系统误差,从而影响因果发现的结果。此次分享的第一个部分将先介绍不同的丢失机制,并在因果图中表示数据丢失机制;然后依此回答:
- 哪些丢失机制会带来系统误差?
- 系统误差会给因果发现带来什么影响?
- 如何找出可能错误的因果关系?
- 如何能够在潜在错误的因果关系中还原回正确的因果关系?
此次分享第一个部分的最后将在此次分享中介绍关于评估因果发现方法的困难和现状。
因果发现算法
分享者:黄碧薇 卡耐基梅隆大学博士在读
因果发现能够在不引入先验知识的情况下,自动化地在大规模时序数据中找到因果联系,本次会详细介绍因果发现的两类方法: 基于条件约束的方法 (constraint-based methods) 的和基于功能因果模型的方法 (functional causal model-based approaches)。
对于基于条件约束的方法,我们除了介绍well-known的PC算法和FCI算法,还会进一步探讨最新的进展。比如当部分数据缺失时,或者非稳态的情况下,如何实现因果发现?
对于基于功能因果模型的方法,我们会着重讨论LiNGAM, nonlinear additive-noise model, 以及post-nonlinear model。并且会进一步拓展到当出现cycle, 或者存在hidden confounder的情况。
文章推荐
会议预告丨CLeaR (Causal Learning and Reasoning) 2022国际会议4月11-13日举办 | 集智俱乐部 (swarma.org)
causal-learn:基于Python的因果发现算法平台 | 集智俱乐部 (swarma.org)
因果发现最新进展及其在电信网络运营维护的实践探讨 | 集智俱乐部 (swarma.org)
因果科学入门读什么书?Y. Bengio博士候选人的研读路径推荐
历时3个月,全球32位讲者,共同讲述因果科学与Causal AI的全景框架!
相关路径
- 因果科学与Casual AI读书会必读参考文献列表,这个是根据读书会中解读的论文,做的一个分类和筛选,方便大家梳理整个框架和内容。
- 因果推断方法概述,这个路径对因果在哲学方面的探讨,以及因果在机器学习方面应用的分析。
- 因果科学和 Causal AI入门路径,这条路径解释了因果科学是什么以及它的发展脉络。此路径将分为三个部分进行展开,第一部分是因果科学的基本定义及其哲学基础,第二部分是统计领域中的因果推断,第三个部分是机器学习中的因果(Causal AI)。
- ↑ Spirtes, Peter, et al. Causation, prediction, and search. MIT press, 2000.