Carnegie Mellon University

Kun Zhang

Kun Zhang

Assistant Professor

Bio

Kun Zhang is an assistant professor in the CMU philosophy department and an affiliate faculty member in the machine learning department. His research interests lie in machine learning and artificial intelligence, especially in causal discovery and causality-based learning. He develops methods for automated causal discovery from various kinds of data, investigates learning problems including transfer learning and deep learning from a causal view, and studies philosophical foundations of causation and machine learning. On the application side, he is interested in neuroscience, computational finance, and climate analysis.

Research

Causal discovery: Theory, algorithms, and applications

  • Practical computational methods for causal discovery and inference
  • Data analytics from a causal perspective
  • Fundamental and testable principles to characterize causality
  • Latent variable modeling


Statistical machine learning and applications (especially from a causal perspective)

  • Domain adaptation/transfer learning
  • Learning in nonstationary/heterogeneous environments
  • Kernel distribution embedding
  • Gaussian processes, semi-supervised learning
  • Mixture models
  • Model selection
  • Independent component analysis
  • Sparse coding


Neuroscience (especially fMRI, MEG, and EEG data analysis), climate analysis, and healthcare


Computational finance

  • Volatility modeling and risk management
  • Factor models in finance
  • Causality in finance

Academic Service

Organizational activities:

  • Co-organizer of the 2017 ACM SIGKDD Workshop on Causal Discovery (with Lin Liu, Jiuyong Li, Emre Kiciman, and Negar Kiyavash)
  • Co-organizer of the UAI 2017 workshop on causality (with Elias Bareinboim, Caroline Uhler, Jiji Zhang, and Dominik Janzing)
  • Co-organizer of AMIA 2017 Pre-symposium Workshops on Data Mining for Medical Informatics (DMMI) – Causal Inference for Health Data Analytics (with Kenney Ng, Bisakha Ray, SiSi Ma, and Fei Wang)
  • Co-organizer of Workshop “Causality: Dialogues between Machine Learning and Psychology” at Data Learning and Inference 2017 (DALI’17), April 18, 2017 (with David Danks and Felix Wichmann)
  • Co-organizer of the Munich Workshop on Causal Inference and Information Theory (MCI), May 23-24, 2016 (with Negar Kiyavash and Gerhard Kramer)
  • Co-organizer of the 2016 ACM SIGKDD Workshop on Causal Discovery (With Jiuyong Li, Elias Bareinboim, and Lin Liu)
  • Guest editor of the Journal of Data Science and Analytics Special Issue on Causal Discovery (with Jiuyong Li, Elias Bareinboim, and Lin Liu), 2016
  • Organizer of workshop “Causal modeling & machine learning” at ICML 2014, Beijing, China, June, 2014 (with Bernhard Schölkopf , Eias Bareinboim, and Jiji Zhang)
  • Guest editor of the ACM Transactions on Intelligent Systems and Technologies (ACM TIST) Special Issue on Causal Discovery and Inference (with Jiuyong Li, Elias Bareinboim, Bernhard Schölkopf, and Judea Pearl), 2013 - 2014
  • Organizer of workshop “Causality: Perspectives from different disciplines,” Vals, Switzerland, August, 2013 (with Jiji Zhang and Bernhard Schölkopf)
  • Co-organizer and program chair of the First IEEE / ICDM Workshop on Causal Discovery (CD 2013, with Jiuyong Li, Lin Liu, and Jian Pei)
  • Co-organizer of IJCNN’13 cause-effect pairs challenge (causality challenge #3)
  • Co-organizer of workshop “Networks -- Processes and causality,” Menorca, Spain, September, 2012 (with Manuel G. Rodriguez, and Bernhard Schölkopf)
  • Publicity chair of AISTATS 2012 (15th International Conference on Artificial Intelligence and Statistics)
  • Organizer and chair of special session on ICA at ICONIP 2006

Reviewer for journals:

  • Annals of Statistics
  • Journal of Machine Learning Research
  • Annals of Applied Statistics
  • Journal of the American Statistical Association
  • Neural Computation
  • Machine Learning
  • Artificial Intelligence
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • IEEE Transactions on Neural Networks and Learning Systems
  • IEEE Transactions on Signal Processing; Neural Networks
  • IEEE Transactions on Knowledge and Data Engineering
  • Journal of Royal Statistical Society: Series C
  • British Journal for the Philosophy of Science
  • Computational Statistics
  • Computer Vision and Image Understanding
  • Quantitative Finance
  • Neurocomputing
  • Behaviormetrika
  • Computational Statistics
  • Computer Vision and Image Understanding
  • International Journal of Bioinformatics Research and Applications
  • European Journal of Operational Research
  • Inverse Problems and Imaging
  • IEEE Signal Processing Letters
  • Frontiers of Computer Science
  • International Journal of Imaging Systems and Technology
  • Circuits, Systems & Signal Processing
  • International Review of Economics and Finance

Program committee member for international conferences:

  • 2018: ICLR, ICML (area chair)
  • 2017: AISTATS (senior PC), IJCAI (senior PC), ICML, AAAI, KDD, AMBN, UAI, NIPS (area chair), ACML (senior PC)
  • 2016: AISTATS (senior PC), IJCAI (senior PC), ICML, KDD (research track), NIPS (area chair), AAAI, UAI (senior PC)
  • 2015: AISTATS, KDD, UAI, IJCAI, ECML-PKDD, NIPS
  • 2014: AISTATS (senior PC), WSDM, KDD (research & industry tracks), iKDD CoDS, UAI, NIPS, ACML
  • 2013: UAI, NIPS, AISTATS, SDM, KDD, IJCAI, IJCNN, Big Data
  • 2012: UAI, AISTATS, MLSP, WSDM, SDM
  • 2011: NIPS, UAI, KDD, IJCNN, ICONIP
  • 2010: NIPS, UAI, ICA/LVA, SDM, ACML, ICPR, ICNC-FSKD
  • 2009: NIPS, ACML, ICONIP
  • 2007: MLSP, IDEAL, ISNN
  • 2006: ICONIP, DSN; 2005: PhysCon

Recent Publications

  • Kun Zhang, Bernhard Schölkopf, Peter Spirtes, Clark Glymour, “Learning Causality and Causality-Related Learning,” National Science Review, to appear
  • Biwei Huang, Kun Zhang, Jiji Zhang, Ruben Sanchez Romero, Clark Glymour, Bernhard Schölkopf, “Behind Distribution Shift: Mining Driving Forces of Changes and Causal Arrows,” accepted to IEEE 17th International Conference on Data Mining (ICDM 2017), 2017
  • AmirEmad Ghassami, Saber Salehkaleybar, Negar Kiyavash, Kun Zhang, “Learning Causal Structures Using Regression Invariance,” accepted to Advances in Neural Information Processing Systems 30 (NIPS 2017), 2017
  • Kun Zhang, Mingming Gong, Joseph Ramsey, Kayhan Batmanghelich, Peter Spirtes, Clark Glymour , Causal Discovery in the Presence of Measurement Error: Identifiability Conditions, UAI workshop on causality, 2017
  • Mingming Gong, Kun Zhang, Bernhard Schölkopf, Clark Glymour, and Dacheng Tao, Causal Discovery from Temporally Aggregated Time Series, Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence (UAI 2017), 2017
  • Aditya Menon, Chetali Gupta, Kedar M. Perkins, Brian L. DeCost, Nikita Budwal, Renee T. Rios, Kun Zhang, Barnabás Póczosd and Newell R. Washburn, Elucidating multi-physics interactions in suspensions for the design of polymeric dispersants: a hierarchical machine learning approach, Molecular Systems Design & Engineering, 2017
  • Kun Zhang, Biwei Huang, Jiji Zhang, Clark Glymour, Bernhard Schölkopf, "Causal Discovery in the Presence of Distribution Shift: Skeleton Estimation and Orientation Determination," in Proc. International Joint Conference on Artificial Intelligence (IJCAI 2017), Melbourne, Australia, August, 2017
  • Hao Zhang, Shuigeng Zhou, Kun Zhang, Jihong Guan, “Causal Discovery Using Regression-Based Conditional Independence Tests,” in Proc. 31th AAAI Conference on Artificial Intelligence (AAAI 2017), San Franceso, USA, Feb., 2017
  • Heng Peng, Tao Huang, and Kun Zhang, “Model Selection for Gaussian Mixture Models," Statistica Sinica, Jan., 2017
  • Peter Spirtes and Kun Zhang, “Causal discovery and inference: Concepts and recent methodological advances.” Applied Informatics, 3(3), 2016
  • Kun Zhang, Jiji Zhang, Biwei Huang, Bernhard Schölkopf, Clark Glymour, “On the Identifiability and Estimation of Functional Causal Models in the Presence of Outcome-Dependent Selection,” Proceedings of the 32rd Conference on Uncertainty in Artificial Intelligence (UAI 2016), 2016 (plenary talk session)
  • Jalal Etesam, Negar Kiyavash, Kun Zhang, and Kushagra Singhal, “Learning Causal Interaction Network of Multivariate Hawkes Processes,” Proceedings of the 32rd Conference on Uncertainty in Artificial Intelligence (UAI 2016), 2016
  • MingmingGong, Kun Zhang, Tongliang Liu, Dacheng Tao, Clark Glymour, and Bernhard Schölkopf, “Domain Adaptation with Conditional Transferable Components,” Proceedings of the 33nd International Conference on Machine Learning (ICML 2016), 2016
  • Kun Zhang and Aapo Hyvärinen, “Nonlinear functional causal models for distinguishing cause from effect,” in Statistics and Causality: Methods for Applied Empirical Research, (Ed) W Wiedemann and A von Eye, 2016
  • Kun Zhang, Zhikun Wang, Jiji Zhang, and Bernhard Schölkopf, “On estimation of functional causal models: Post-nonlinear causal model as an example,” ACM Transactions on Intelligent Systems and Technologies, 7(2), 2016
  • Kun Zhang, with Jiuyong Li, Blias Bareinboim, Bernhard Schölkopf, and Judea Pearl, Special Issue of ACM Transactions on Intelligent Systems and Technologies on “Causal Inference and Discovery,” Volume 7, Issue 2, 2016
  • Jiji Zhang and Kun Zhang, “Likelihood and Consilience: On Forster's Counterexamples to the Likelihood Theory of Evidence,” Philosophy of Science, Supplementary Volume 2015
  • Peter Spirtes and Kun Zhang, “Recent Methodological Advances in Causal Discovery and Inference,” In 15th Conference on Theoretical Aspects of Rationality and Knowledge, TARK, 2015
  • Peter Geiger, Kun Zhang, Bernhard Schölkopf, Mingming Gong, and Dominik Janzing, “Causal Inference by Identification of Vector Autoregressive Processes with Hidden Components,” In Proceedings of the 32nd International Conference on Machine Learning (ICML 2015), (Ed) F. Bach and D. Blei, 37, JMLR W&CP, 1917–1925, Lille, France, July 2015
  • Mingming Gong*, Kun Zhang*, Bernhard Schölkopf, Dacheng Tao, and Philipp Geiger, “Discovering Temporal Causal Relations from Subsampled Data,” In Proceedings of the 32nd International Conference on Machine Learning (ICML 2015), (Ed) F. Bach and D. Blei, 37, JMLR W&CP, 1898–1906, Lille, France, July 2015
  • Kun Zhang, Jiji Zhang and Bernhard Schölkopf, "Causal inference based on exogeneity,” Distinguishing Cause from Effect Based on Exogeneity In Proc. Fifteenth Conference on Theoretical Aspects of Rationality and Knowledge, (TARK 2015), Pittsburgh, PA, June 2015
  • Peter Spirtes and Kun Zhang. Recent Methodological Advances in Causal Discovery and Inference In Proc. 15th Conference on Theoretical Aspects of Rationality and Knowledge (TARK 2015), Invited paper, Pittsburgh, PA, June 2015
  • Biwei Huang, Kun Zhang and Bernhard Schölkopf, “Time-dependent causal modeling: A Gaussian process treatmean,” In Proc. 24th International Joint Conference on Artificial Intelligence (IJCAI’15), Machine Learning Track, Argentina, July 2015
  • Kun Zhang, Mingming Gong and Bernhard Schölkopf, “Domain adaptation with multiple sources: A Causal view,” in Proc. 29th AAAI Conference on Artificial Intelligence (AAAI 2015), Austin Texas, USA, Jan., 2015
  • Zhitang Chen, Kun Zhang, Laiwan Chan, and Bernhard Schölkopf, “Causal discovery via reproducing kernel Hilbert space embeddings,” Neural Computation, 26(7):1484-517, 2014
  • Gary Doran, Krikamol Muandet, Kun Zhang, and Bernhard Schölkopf, “A permutation-based kernel conditional independence test,” in Proc. 30th Uncertainty in Artificial Intelligence (UAI 2014), Canada, July 2014 (plenary talk session).
  • Kun Zhang, Bernhard Schölkopf, Krikamol Muandet, Zhikun Wang, Zhi-Hua Zhou, and Claudio Persello, “Single-source domain adaptation with target and conditional shift,” in Regularization, Optimization, Kernels, and Support Vector Machines, J. A. K. Suykens, M. Signoretto, and Andreas Argyriou (Editors), 2014.
  • Kun Zhang, Bernhard Schölkopf, Krikamol Muandet, and Zhikun Wang, "Domain adaptation under target and conditional shift,” Proc. 29th International Conference on Machine Learning (ICML 2013), Atlanta, USA (full oral presentation).
  • Kun Zhang and Zhikun Wang, “On estimation of functional causal models: Post-nonlinear causal model as an example,” First IEEE/ICDM workshop on causal discovery, Dallas, USA, Dec., 2013
  • Zhitang Chen, Kun Zhang, and Laiwan Chan, "Nonlinear Causal Discovery for High Dimensional Data: A Kernelized Trace Method," 2013 IEEE International Conference on Data Mining (ICDM'13), Dallas, USA, Dec., 2013.
  • Bernhard Schölkopf, Dominik Janzing, Jonas Peters, Eleni Sgouritsa, Kun Zhang, and Joris Mooij, "Semi-supervised learning in causal and anticausal settings,” in Festschrift for Vladimir Vapnik's 75th birthday, 2013.
  • Dominik Janzing, Joris Mooij, Kun Zhang, Jan Lemeire, Jakob Zscheischler, Povilas Daniuvsis, Bastian Steudel,  Bernhard Schölkopf, “Information-geometric approach to inferring causal directions,” Artificial Intelligence, pp. 1-31, 2012
  • Zhitang Chen, Kun Zhang and Laiwan Chan, “Causal discovery with scale-mixture model for spatiotemporal variance dependencies,” in Advances in Neural Information Processing Systems 25 (NIPS 2012), Lake Tahoe, Nevada, United States.
  • Bernhard Schölkopf, Dominik Janzing, Jonas Peters, Eleni Sgouritsa, Kun Zhang, and Joris Mooij, "On causal and anticausal learning,” in Proc. 29th International Conference on Machine Learning (ICML 2012), Edinburgh, Scotland, June 2012.
  • Kun Zhang, Jonas Peters, Dominik Janzing, and Bernhard Schölkopf, "Kernel-based conditional independence test and application in causal discovery,” in Proc. 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011), Barcelona, Spain, July 2011.
  • Jakob Zscheischler, Dominik Janzing, and Kun Zhang, "Testing whether linear equations are causal: A free probability theory approach,” in Proc. 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011), Barcelona, Spain, July 2011.
  • Kun Zhang and Aapo Hyvärinen, "A general linear non-Gaussian state-space model: Identifiability, identification, and application,” in Proc. 3rd Asian Conference on Machine Learning (ACML 2011), Taoyuan, Taiwan, Nov. 2011.
  • Aapo Hyvärinen, Kun Zhang, Shohei Shimizu, and Patrik Hoyer, "Estimation of a structural vector autoregression model using non-Gaussianity," Journal of Machine Learning Research, 11, pp. 1709-1731, 2010.
  • Kun Zhang and Lai-Wan Chan, "Convolutive blind source separation by efficient blind deconvolution and minimal filter distortion," Neurocomputing, 73(13-15) 2580-2588, 2010.
  • Joris Mooij, Oliver Stegle, Dominik Janzing, Kun Zhang, and Bernhard Schölkopf, “Probabilistic latent variable models for distinguishing between cause and effect,” in Advances in Neural Information Processing Systems 23, (NIPS 2010), Curran, NY, USA, 1687-1695.
  • Kun Zhang, Bernhard Schölkopf, and Dominik Janzing, "Invariant gaussian process latent variable models and application in causal discovery,” in Proc. 26th Conference on Uncertainty in Artificial Intelligence (UAI 2010), California, July 2010 (plenary talk session).
  • Kun Zhang and Aapo Hyvärinen, "Source separation and higher-order causal analysis of MEG and EEG,” in Proc. 26th Conference on Uncertainty in Artificial Intelligence (UAI 2010), California, July 2010 (acceptance rate ~ 30%).
  • Povilas Daniusis, Dominik Janzing, Joris Mooij, Jakob Zscheischler, Bastian Steudel, Kun Zhang, Bernhard Schölkopf, "Inferring deterministic causal relations,” in Proc. 26th Conference on Uncertainty in Artificial Intelligence (UAI 2010), California, July 2010 (plenary talk session).
  • Min-Ling Zhang and Kun Zhang, "Multi-label learning by exploiting label dependency,” in Proc. ACM SIGKDD conference on Knowledge Discovery and Data Mining (KDD2010), Washington DC, July 2010.
  • Kun Zhang and Aapo Hyvärinen, "Acyclic causality discovery with additive noise: An information-theoretical perspective,” in Proc. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) 2009, Bled, Slovenia, pp. 570--585, 2009.
  • Kun Zhang and Lai-Wan Chan, "Efficient factor GARCH models and factor-DCC models," Quantitative Finance , 9(1), pp. 71--91, 2009.
  • Kun Zhang and Aapo Hyvärinen, "On the identifiability of the post-nonlinear causal model,” in Proc. 25th Conference on Uncertainty in Artificial Intelligence (UAI 2009), Montreal, Canada, 2009 (plenary talk session).
  • Kun Zhang, Heng Peng, Laiwan Chan, and Aapo Hyvärinen, "ICA with sparse connections: Revisited,” in Proc. 8th Int. Conference on Independent Component Analysis and Signal Separation (ICA 2009), Paraty, Brazil, pp. 195--202, 2009.
  • Kun Zhang and Aapo Hyvärinen, "Distinguishing causes from effects using nonlinear acyclic causal models,” in JMLR Workshop and Conference Proceedings, Volume 6, pp. 157-164, 2010 (presented at NIPS 2008 workshop on causality).  Best Benchmark Award
  • Kun Zhang and Lai-Wan Chan, "Minimal nonlinear distortion principle for nonlinear ICA," Journal of Machine Learning Research, 9, pp. 2455--2487, 2008.
  • Kun Zhang and Lai-Wan Chan,"Separating convolutive mixtures by pairwise mutual information minimization,” IEEE Signal Processing Letters, 14(12), pp. 992--995, 2007.
  • Kun Zhang and Laiwan Chan, "Kernel-based nonlinear independent component analysis,” in Proc. 7th Int. Conference on Independent Component Analysis and Signal Separation (ICA 2007), London, UK, pp. 301--308, Sept., 2007.
  • Kun Zhang and Laiwan Chan, "Nonlinear independent component analysis with minimum nonlinear distortion,” the 24th Annual International Conference on Machine Learning (ICML 2007), Corvallis, OR, US, pp. 1127--1134, Jun., 2007.
  • Jian Li, Kun Zhang, and Laiwan Chan, "Portfolio construction by reinforcement learning of independent factors,” in Proc. of the 8th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2007), pp. 1020--1031, 2007.
  • Wan Zhang, Liu Wenyin, and Kun Zhang, "Symbol recognition with kernel density matching,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(12), pp. 2020--2024, 2006.
  • Kun Zhang and Lai-Wan Chan, "An adaptive method for subband decomposition ICA,” Neural Computation, 18(1), pp. 191--223, 2006.
  • Kun Zhang and Lai-Wan Chan, "Dimension reduction as a deflation method in ICA,” IEEE Signal Processing Letters, 13(1), pp. 45--48, 2006.
  • Kun Zhang and Lai-Wan Chan, "Extended Gaussianization method for blind separation of post-nonlinear mixtures,” Neural Computation, 17(2), pp. 425--452, 2006.
  • Kun Zhang and Lai-Wan Chan,  "Extensions of ICA for causality discovery in the Hong Kong stock market,”  in Proc. 13th International Conference on Neural Information Processing (ICONIP 2006),  Hong Kong, Oct., 2006.
  • Kun Zhang and Lai-Wan Chan,  "Enhancement of source independence for blind source separation,”  in Proc. 6th International Conference on Independent Component Analysis and Blind Signal Separation (ICA 2006), LNCS 3889, Charleston, SC, USA, pp. 731--738, Mar., 2006.
  • Kun Zhang and Lai-Wan Chan,  "ICA by PCA approach: relating higher-order statistics to second-order moments,” in Proc. 6th International Conference on Independent Component Analysis and Blind Signal Separation (ICA 2006), LNCS 3889, Charleston, SC, USA, pp. 311--318, Mar., 2006.
  • Kun Zhang and Lai-Wan Chan,  "ICA with sparse connections,” in Proc. 7th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2006), Burgos, Spain, pp. 530--537, Sep., 2006.