Ei_header
Thumb_kun_zhang
Kun Zhang
Dr.
Position: Senior Research Scientist
Room no.: 208
Phone: +49 7071 601-563
Fax: +49 7071 601 552

There has been a long history of debate on causality in philosophy, statistics, economics, and related fields. I have been concerned with this classic question—how can we discover causal information from purely observed data (i.e., perform causal inference)?  How such causal information can facilitate solving other problems such as modeling, prediction, and control, is also interesting to me.

 

My research consists of three main lines.

-- Firstly, I have focused on developing practical computational methods for causal inference, to produce more reliable causal information.

-- Secondly, to better understand causality and derive more universal methods for causal inference, I also work on finding fundamental and testable principles that help discover causality from data.

-- Thirdly, latent variable modeling is closely related to causality, and it has been interesting me for over eight years. Developing more general yet identifiable latent variable models would benefit the causality field, as well as the machine learning and signal processing communities.

Since machine learning plays a key role in data analysis as well as causal inference, I am also very interested in this field.

 

*What's new*

--  The workshop "Causal modeling & machine learning" will take place in Beijing, China, in June 2014.

--  We are editing the ACM Transactions on Intelligent Systems and Technologies (ACM TIST) special issue on causal discovery and inference; see the call for papers here.  Submission deadline: 14 March 2014.

--  The workshop "Causality: Perspectives from different disciplines" took place in August, 2013.

-- Slides and poster for a recent paper "Domain adaptation under target and conditional shift."

Ongoing projects:

- fundamental characterization of causal information in observational data, and refinement of concepts related to causality

 

- precise notion of “model complexity” for causal inference

 

- unified/universal approach for causal inference

 

- domain-specific causal inference (in finance, brain signal analysis, etc.)

 

- causal understanding of machine learning tasks

 

- practical causal inference system for large-scale problems

 

- domain adaptation

 

- big data analytics: a causal perspective

 

- computational finance

Research Interests

· Causal discovery: Theory and applications

o developing advanced and practical computational methods for causal inference

o finding fundamental and testable principles to characterize causality

o latent variable modeling

· Statistical machine learning and applications

o kernel methods, Gaussian processes, domain adaptation, mixture models, model selection, independent component analysis, sparse coding

· Computational finance

· Neuroscience (especially MEG and EEG data analysis)

 

Academic Service

· Organizational activities

o Organizer of ICML'14 workshop "Causal modeling and machine learning" (with Bernhard Schölkopf, Elias Bareinboim, and Jiji Zhang), June, 2014

o Guest editor of ACM Transactions on Intelligent Systems and Technologie special issue on Causality (with Jiuyong Li, Elias Bareinboim, Bernhard Schölkopf, and Judea Pearl)

o Organizer of workshop "Causality: Perspectives from different disciplines" (with Bernhard Schölkopf and Jiji Zhang), Vals, Switzerland, August 5-8, 2013

o Co-organizer of the First IEEE ICDM Workshop on Causal Discovery (CD 2013), Dallas, Texas, USA, December 8, 2013

o Co-organizer of workshop “Networks -- Processes and causality”, Menorca, Spain, September, 2012

o Publicity chair of AISTATS 2012 (15th International Conference on Artificial Intelligence and Statistics)

· Reviewer for journals

o Annals of Statistics; Journal of Machine Learning Research; Annals of Applied Statistics; Journal of the American Statistical Association; Neural Computation; Machine Learning; IEEE Transactions on Pattern Analysis and Machine Intelligence; IEEE Transactions on Neural Networks; IEEE Transactions on Signal Processing; Neural Networks; IEEE Transactions on Knowledge and Data Engineering; Quantitative Finance; Neurocomputing; 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

o 2014: AISTATS (senior program committee), UAI, NIPS, WSDM, KDD, iKDD CoDS...

o 2013: UAI, NIPS, AISTATS, SDM, KDD, IJCAI, IJCNN, ASE/IEEE Big Data;

o 2012: UAI, AISTATS, MLSP, WSDM, SDM;

o 2011: UAI, NIPS, KDD, IJCNN, ICONIP;

o 2010: UAI, NIPS, ICA/LVA, SDM, ACML, ICPR;

o 2009: NIPS, ACML, ICONIP


Export search results as: [BibTex]

2015
Conference Papers
2014
Articles
  • J. Zhang, K. Zhang (2014). Likelihood and Consilience: On Forster’s Counterexamples to the Likelihood Theory of Evidence Philosophy of Science, Supplementary Volume 2015, State: accepted
  • K. Zhang, Z. Wang, J. Zhang, B. Schölkopf (2014). On estimation of functional causal models: General results and application to post-nonlinear causal model ACM Transactions on Intelligent Systems and Technologies, State: accepted
Contributions to books
Conference Papers
  • G. Doran, K. Muandet, K. Zhang, B. Schölkopf (2014). A Permutation-Based Kernel Conditional Independence Test In: Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence (UAI2014), (Ed) Nevin L. Zhang and Jin Tian, AUAI Press Corvallis, Oregon, 132–141, UAI2014
2013
Contributions to books
Conference Papers
  • Z. Chen, K. Zhang, L. Chan (2013). Nonlinear Causal Discovery for High Dimensional Data: A Kernelized Trace Method IEEE Computer Society, IEEE International Conference on Data Mining (ICDM’13)
2012
Articles
Conference Papers
  • Z. Chen, K. Zhang, L. Chan (2012). Causal discovery with scale-mixture model for spatiotemporal variance dependencies In: Advances in Neural Information Processing Systems 25, (Ed) P Bartlett and FCN Pereira and CJC. Burges and L Bottou and KQ Weinberger, Curran Associates Inc., 1736–1744, 26th Annual Conference on Neural Information Processing Systems (NIPS 2012)
2011
Conference Papers
  • J. Zscheischler, D. Janzing, K. Zhang (2011). Testing whether linear equations are causal: A free probability theory approach (Ed) Cozman, F.G. , A. Pfeffer, AUAI Press, Corvallis, OR, USA, 839-847, ISBN: 978-0-9749039-7-2, 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011)
  • K. Zhang, J. Peters, D. Janzing, B. Schölkopf (2011). Kernel-based Conditional Independence Test and Application in Causal Discovery (Ed) FG Cozman and A Pfeffer, AUAI Press, Corvallis, OR, USA, 804-813, ISBN: 978-0-9749039-7-2, 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011)
  • K. Zhang, A. Hyvärinen (2011). A general linear non-Gaussian state-space model: Identifiability, identification, and applications In: JMLR Workshop and Conference Proceedings Volume 20, (Ed) Hsu, C.-N. , W.S. Lee , MIT Press, Cambridge, MA, USA, 113-128, 3rd Asian Conference on Machine Learning (ACML 2011)
2010
Conference Papers
  • Zhang, K. and Hyvärinen, A. (2010). Distinguishing Causes from Effects using Nonlinear Acyclic Causal Models In: JMLR Workshop and Conference Proceedings, Volume 6, (Ed) I Guyon and D Janzing and B Schölkopf, MIT Press, Cambridge, MA, USA, 157-164, Causality: Objectives and Assessment (NIPS 2008 Workshop)
  • K. Zhang, A. Hyvärinen (2010). Source Separation and Higher-Order Causal Analysis of MEG and EEG (Ed) Grünwald, P. , P. Spirtes, Uncertainty in Artificial Intelligence: Proceedings of the Twenty-Sixth Conference (UAI 2010), AUAI Press, Corvallis, OR, USA, 709-716, ISBN: 978-0-9749039-6-5, 26th Conference on Uncertainty in Artificial Intelligence (UAI 2010)
  • K. Zhang, B. Schölkopf, D. Janzing (2010). Invariant Gaussian Process Latent Variable Models and Application in Causal Discovery In: Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, (Ed) P Grünwald and P Spirtes, Uncertainty in Artificial Intelligence: Proceedings of the Twenty-Sixth Conference (UAI 2010), AUAI Press, Corvallis, OR, USA, 717-724, ISBN: 978-0-9749039-6-5, UAI 2010
  • M-L. Zhang, K. Zhang (2010). Multi-Label Learning by Exploiting Label Dependency (Ed) Rao, B. , B. Krishnapuram, A. Tomkins, Q. Yang, Proceedings of the 16th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2010), ACM Press, New York, NY, USA, 999-1008, 16th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2010)
  • JM. Mooij, O. Stegle, D. Janzing, K. Zhang, B. Schölkopf (2010). Probabilistic latent variable models for distinguishing between cause and effect In: Advances in Neural Information Processing Systems 23, (Ed) J Lafferty and CKI Williams and J Shawe-Taylor and RS Zemel and A Culotta, Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, Curran, Red Hook, NY, USA, 1687-1695, ISBN: 978-1-617-82380-0, 24th Annual Conference on Neural Information Processing Systems (NIPS 2010)
Articles
  • Hyvärinen, A. and Zhang, K. and Shimizu, S. and Hoyer, P. (2010). Estimation of a Structural Vector Autoregression Model Using Non-Gaussianity Journal of Machine Learning Research, 11, 1709-1731
  • K. Zhang, L-W. Chan (2010). Convolutive blind source separation by efficient blind deconvolution and minimal filter distortion Neurocomputing, 73, (13-15), 2580-2588
2009
Articles
  • Zhang, K. and Chan, L. (2009). Efficient factor GARCH models and factor-DCC models Quantitative Finance, 9, (1), 71-91
Conference Papers
  • Zhang, K. and Peng, H. and Chan, L. and Hyvärinen, A. (2009). ICA with Sparse Connections: Revisited In: Independent Component Analysis and Signal Separation, (Ed) Adali, T. , Christian Jutten, J.M. Travassos Romano, A. Kardec Barros, Springer, Berlin, Germany, 195-202, ISBN: 978-3-642-00599-2, 8th International Conference on Independent Component Analysis and Signal Separation (ICA 2009)
  • Zhang, K. and Hyvärinen, A. (2009). Causality Discovery with Additive Disturbances: An Information-Theoretical Perspective In: Machine Learning and Knowledge Discovery in Databases, (Ed) Buntine, W. , M. Grobelnik, D. Mladenić, J. Shawe-Taylor , Springer, Berlin, Germany, 570-585, ISBN: 978-3-642-04174-7, European Conference on Machine Learning and Knowledge Discovery in Databases: Part II (ECML PKDD ’09)
  • Zhang, K. and Hyvärinen, A. (2009). On the Identifiability of the Post-Nonlinear Causal Model (Ed) Bilmes, J. , A. Y. Ng, D. A. McAllester, Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence (UAI 2009), AUAI Press, Corvallis, OR, USA, 647-655, ISBN: 978-0-9749039-5-8 , 25th Conference on Uncertainty in Artificial Intelligence (UAI 2009)
2008
Articles
  • Zhang, K. and Chan, L. (2008). Minimal Nonlinear Distortion Principle for Nonlinear Independent Component Analysis Journal of Machine Learning Research, 9, 2455-2487
2007
Articles
  • Zhang, K. and Chan, L. (2007). Separating convolutive mixtures by pairwise mutual information minimization", IEEE Signal Processing Letters IEEE Signal Processing Letters, 14, (12), 992-995
Conference Papers
  • Zhang, K. and Chan, L. (2007). Kernel-Based Nonlinear Independent Component Analysis In: Independent Component Analysis and Signal Separation, 7th International Conference, ICA 2007, (Ed) M E Davies and C J James and S A Abdallah and M D Plumbley, Springer, 301-308, 7th International Conference on Independent Component Analysis and Signal Separation (ICA 2007)
  • Li, J. and Zhang, K. and Chan, L. (2007). Independent Factor Reinforcement Learning for Portfolio Management In: Proceedings of the 8th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2007), (Ed) H Yin and P Tiño and E Corchado and W Byrne and X Yao, Springer, Berlin, Germany, 1020-1031, 8th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2007)
  • Zhang, K. and Chan, L. (2007). Nonlinear independent component analysis with minimum nonlinear distortion In: ICML ’07: Proceedings of the 24th international conference on Machine learning, (Ed) Z Ghahramani, ACM, New York, NY, USA, 1127-1134, 24th International Conference on Machine Learning (ICML 2007)
2006
Articles
  • Zhang, W. and Wenyin, L. and Zhang, K. (2006). Symbol Recognition with Kernel Density Matching IEEE Transactions on Pattern Analysis and Machine Intelligence, 28, (12), 2020-2024
  • Zhang, K. and Chan, L. (2006). Dimension Reduction as a Deflation Method in ICA IEEE Signal Processing Letters, 13, (1), 45-48
  • Zhang, K. and Chan, L. (2006). An adaptive method for subband decomposition ICA Neural Computation, 18, (1), 191-223
Conference Papers
  • Zhang, K. and Chan, L. (2006). Enhancement of source independence for blind source separation In: Independent Component Analysis and Blind Signal Separation, LNCS 3889, (Ed) J. Rosca and D. Erdogmus and JC Príncipe und S. Haykin, Springer, Berlin, Germany, 731-738, 6th International Conference on Independent Component Analysis and Blind Signal Separation (ICA 2006)
  • Zhang, K. and Chan, L. (2006). ICA by PCA Approach: Relating Higher-Order Statistics to Second-Order Moments In: Independent Component Analysis and Blind Signal Separation, (Ed) J P Rosca and D Erdogmus and J C Príncipe and S Haykin, Springer, 311-318, 6th International Conference on Independent Component Analysis and Blind Signal Separation (ICA 2006)
  • Zhang, K. and Chan, L. (2006). Extensions of ICA for Causality Discovery in the Hong Kong Stock Market In: Neural Information Processing, 13th International Conference, ICONIP 2006, (Ed) I King and J Wang and L Chan and D L Wang, Springer, 400-409, 13th International Conference on Neural Information Processing (ICONIP 2006)
  • Zhang, K. and Chan, L. (2006). ICA with Sparse Connections In: Intelligent Data Engineering and Automated Learning – IDEAL 2006, (Ed) E Corchado and H Yin and V Botti und Colin Fyfe, Springer, 530-537, 7th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2006)
2005
Articles
  • Zhang, K. and Chan, L. (2005). Extended Gaussianization Method for Blind Separation of Post-Nonlinear Mixtures Neural Computation, 17, (2), 425-452
Conference Papers
  • Zhang, K. and Chan, L. (2005). To apply score function difference based ICA algorithms to high-dimensional data In: Proceedings of the 13th European Symposium on Artificial Neural Networks (ESANN 2005), 291-297, 13th European Symposium on Artificial Neural Networks (ESANN 2005)
2004
Conference Papers
  • Zhang, K. and Chan, L. (2004). Practical Method for Blind Inversion of Wiener Systems In: Proceedings of International Joint Conference on Neural Networks (IJCNN 2004), 2163-2168, International Joint Conference on Neural Networks (IJCNN 2004)
2003
Conference Papers
  • Zhang, K. and Chan, L. (2003). Dimension Reduction Based on Orthogonality — a Decorrelation Method in ICA In: Artificial Neural Networks and Neural Information Processing - ICANN/ICONIP 2003, (Ed) O Kaynak and E Alpaydin and E Oja and L Xu, Springer, Berlin, Germany, 132-139, International Conference on Artificial Neural Networks and International Conference on Neural Information Processing, ICANN/ICONIP 2003