Ei_header
Thumb_dominik_janzing
Dominik Janzing
PD Dr.
Position: Senior Research Scientist
Room no.: 215
Phone: +49 7071 601 564
Fax: +49 7071 601 552

Research interests:
- novel causal inference methods and their foundation
- physics of causality and information flow
- notions of complexity and their application in machine learning
- statistical methods
- statistical physics, in particular the link between causality and the second law of thermodynamics. I founded the group ``causal inference'' together with Bernhard Schölkopf. The website can be found here

I have been working on quantum information theory for many years and I'm still interested in it; my current causality research is strongly influenced by the paradigm that information is physical. To see the publications from my previous field visit the following website

Dominik Janzing studied physics in Tübingen (Germany) and Cork (Ireland) and received a Ph.D. in mathematics from the Unversity of Tübingen in 1998. From 1998-2006 he was a postdoc and senior scientist at the Computer Science department of the University of Karlsruhe (TH) where he worked on quantum thermodynamics, quantum control, as well as quantum complexity theory and its physical foundations. Since 2007 he has been working as a senior scientist at the Max Planck Institute for Biological Cybernetics in Tübingen, where he founded the group causal inference together with Bernhard Schölkopf.
The group develops novel methods for causal reasoning from statistical data. These novel approaches use complexity of conditional probability distributions for causal reasoning. The idea is strongly influenced by his previous work on complexity of physical processes and the thermodynamics of information flow.


Export search results as: [BibTex]

2015
Talks
  • R. Chaves, C. Majenz, L. Luft, TO. Maciel, D. Janzing, B. Schölkopf, D. Gross (2015). Information-Theoretic Implications of Classical and Quantum Causal Structures 18th Conference on Quantum Information Processing (QIP 2015), State: accepted
2014
Articles
Conference Papers
  • R. Chaves, L. Luft, TO. Maciel, D. Gross, D. Janzing, B. Schölkopf (2014). Inferring latent structures via information inequalities In: Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence, (Ed) NL Zhang and J Tian, AUAI Press, Corvallis, Oregon, 112-121, UAI 2014
  • P. Geiger, D. Janzing, B. Schölkopf (2014). Estimating Causal Effects by Bounding Confounding In: Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence , (Ed) Nevin L. Zhang and Jin Tian, AUAI Press Corvallis, Oregon , 240-249 , UAI 2014
2013
Articles
Contributions to books
Conference Papers
  • E. Sgouritsa, D. Janzing, J. Peters, B. Schölkopf (2013). Identifying Finite Mixtures of Nonparametric Product Distributions and Causal Inference of Confounders In: Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence (UAI), (Ed) A Nicholson and P Smyth, AUAI Press Corvallis, Oregon, USA, 556-565, UAI 2013
  • J. Peters, D. Janzing, B. Schölkopf (2013). Causal Inference on Time Series using Restricted Structural Equation Models In: Advances in Neural Information Processing Systems 26, (Ed) C.J.C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger, 154-162, 27th Annual Conference on Neural Information Processing Systems (NIPS 2013)
  • J. Mooij, D. Janzing, B. Schölkopf (2013). From Ordinary Differential Equations to Structural Causal Models: the deterministic case In: Proceedings of the Twenty-Ninth Conference Annual Conference on Uncertainty in Artificial Intelligence, (Ed) A Nicholson and P Smyth, AUAI Press, Corvallis, Oregon, 440-448, UAI 2013
2012
Conference Papers
Articles
  • J. Lemeire, D. Janzing (2012). Replacing Causal Faithfulness with Algorithmic Independence of Conditionals Minds and Machines, 1-23
  • AE. Allahverdyan, KV. Hovhannisyan, D. Janzing, G. Mahler (2012). Thermodynamic limits of dynamic cooling Physical Review E, 84, (4), 16 pages
2011
Articles
Conference Papers
  • J. Mooij, D. Janzing, B. Schölkopf, T. Heskes (2011). On Causal Discovery with Cyclic Additive Noise Models In: Advances in Neural Information Processing Systems 24, (Ed) J Shawe-Taylor and RS Zemel and PL Bartlett and FCN Pereira and KQ Weinberger, Curran Associates, Inc., Red Hook, NY, USA, 639-647, Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS 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)
  • M. Besserve, D. Janzing, NK. Logothetis, B. Schölkopf (2011). Finding dependencies between frequencies with the kernel cross-spectral density IEEE, Piscataway, NJ, USA, 2080-2083 , ISBN: 978-1-4577-0538-0 , IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2011)
  • 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)
2010
Proceedings
  • I. Guyon, D. Janzing, B. Schölkopf (2010). JMLR Workshop and Conference Proceedings: Volume 6 MIT Press, Cambridge, MA, USA, 288, ISBN: -, Causality: Objectives and Assessment (NIPS 2008 Workshop)
Articles
  • D. Janzing (2010). On the Entropy Production of Time Series with Unidirectional Linearity Journal of Statistical Physics, 138, (4-5), 767-779
Conference Papers
  • I. Guyon, D. Janzing, B. Schölkopf (2010). Causality: Objectives and Assessment In: JMLR Workshop and Conference Proceedings: Volume 6 , (Ed) I Guyon and D Janzing and B Schölkopf, MIT Press, Cambridge, MA, USA, 1-42, Causality: Objectives and Assessment (NIPS 2008 Workshop)
  • J. Mooij, D. Janzing (2010). Distinguishing between cause and effect In: JMLR Workshop and Conference Proceedings: Volume 6, (Ed) Guyon, I. , D. Janzing, B. Schölkopf, MIT Press, Cambridge, MA, USA, 147-156, Causality: Objectives and Assessment (NIPS 2008 Workshop)
  • B. Steudel, D. Janzing, B. Schölkopf (2010). Causal Markov condition for submodular information measures In: Proceedings of the 23rd Annual Conference on Learning Theory, (Ed) AT Kalai and M Mohri, COLT 2010: The 23rd Annual Conference on Learning Theory, OmniPress, Madison, WI, USA, 464-476, COLT 2010
  • D. Janzing, P. Hoyer, B. Schölkopf (2010). Telling cause from effect based on high-dimensional observations In: Proceedings of the 27th International Conference on Machine Learning, (Ed) J Fürnkranz and T Joachims, Proceedings of the 27th International Conference on Machine Learning (ICML 2010), International Machine Learning Society, Madison, WI, USA, 479-486, ISBN: 978-1-605-58907-7, ICML 2010
  • J. Peters, D. Janzing, A. Gretton, B. Schölkopf (2010). Kernel Methods for Detecting the Direction of Time Series In: Advances in Data Analysis, Data Handling and Business Intelligence, (Ed) A Fink and B Lausen and W Seidel and A Ultsch, Advances in Data Analysis, Data Handling and Business Intelligence, Springer, Gesellschaft für Klassifikation, Berlin, Germany, 57-66, ISBN: 978-3-642-01044-6, 32nd Annual Conference of the Gesellschaft für Klassifikation e.V. (GfKl 2008)
  • 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
  • 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)
  • J. Peters, D. Janzing, B. Schölkopf (2010). Identifying Cause and Effect on Discrete Data using Additive Noise Models In: JMLR Workshop and Conference Proceedings Volume 9: AISTATS 2010, (Ed) YW Teh and M Titterington, Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010), JMLR, Cambridge, MA, USA, 597-604, 13th International Conference on Artificial Intelligence and Statistics
2009
Articles
  • AE. Allahverdyan, D. Janzing, G. Mahler (2009). Thermodynamic efficiency of information and heat flow Journal of Statistical Mechanics: Theory and Experiment, 2009, (P09011), 1-35
Conference Papers
  • JM. Mooij, D. Janzing, J. Peters, B. Schölkopf (2009). Regression by dependence minimization and its application to causal inference in additive noise models In: Proceedings of the 26th International Conference on Machine Learning, (Ed) A Danyluk and L Bottou and M Littman, Proceedings of the 26th International Conference on Machine Learning (ICML 2009), ACM Press, New York, NY, USA, 745-752, ICML 2009
  • PO. Hoyer, D. Janzing, JM. Mooij, J. Peters, B. Schölkopf (2009). Nonlinear causal discovery with additive noise models In: Advances in neural information processing systems 21, (Ed) D Koller and D Schuurmans and Y Bengio and L Bottou, Advances in neural information processing systems 21 : 22nd Annual Conference on Neural Information Processing Systems 2008, Curran, Red Hook, NY, USA, 689-696, ISBN: 978-1-605-60949-2, 22nd Annual Conference on Neural Information Processing Systems (NIPS 2008)
  • J. Peters, D. Janzing, A. Gretton, B. Schölkopf (2009). Detecting the Direction of Causal Time Series In: Proceedings of the 26th International Conference on Machine Learning, (Ed) A Danyluk and L Bottou and ML Littman, Proceedings of the 26th International Conference on Machine Learning (ICML 2009), ACM Press, New York, NY, USA, 801-808, ICML 2009
  • D. Janzing, J. Peters, JM. Mooij, B. Schölkopf (2009). Identifying confounders using additive noise models In: Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, (Ed) J Bilmes and AY Ng, Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence (UAI 2009), AUAI Press, Corvallis, OR, USA, 249-257, ISBN: 978-0-9749039-5-8 , UAI 2009
2008
Articles
  • D. Janzing, P. Wocjan, S. Zhang (2008). A Single-shot Measurement of the Energy of Product States in a Translation Invariant Spin Chain Can Replace Any Quantum Computation New Journal of Physics, 10, (093004), 1-18
  • AE. Allahverdyan, D. Janzing (2008). Relating the Thermodynamic Arrow of Time to the Causal Arrow Journal of Statistical Mechanics, 2008, (P04001), 1-21
2007
Articles
Conference Papers
  • X. Sun, D. Janzing (2007). Learning causality by identifying common effects with kernel-based dependence measures In: ESANN 2007, Proceedings of the 15th European Symposium on Artificial Neural Networks (ESANN 2007), D-Side, Evere, Belgium, 453-458, 15th European Symposium on Artificial Neural Networks
  • X. Sun, D. Janzing (2007). Exploring the causal order of binary variables via exponential hierarchies of Markov kernels In: ESANN 2007, Proceedings of the 15th European Symposium on Artificial Neural Networks (ESANN 2007), D-Side, Evere, Belgium, 465-470, 15th European Symposium on Artificial Neural Networks
  • X. Sun, D. Janzing, B. Schölkopf, K. Fukumizu (2007). A Kernel-Based Causal Learning Algorithm In: Proceedings of the 24th International Conference on Machine Learning(ICML 2007), (Ed) Z Ghahramani, Proceedings of the 24th Annual International Conference on Machine Learning (ICML 2007), ACM Press, New York, NY, USA, 855-862, ICML 2007
  • X. Sun, D. Janzing, B. Schölkopf (2007). Distinguishing Between Cause and Effect via Kernel-Based Complexity Measures for Conditional Distributions In: Proceedings of the 15th European Symposium on Artificial Neural Networks , (Ed) M Verleysen, Proceedings of the 15th European Symposium on Artificial Neural Networks (ESANN 2007), D-Side Publications, Evere, Belgium, 441-446, ESANN 2007
2006
Conference Papers
  • X. Sun, D. Janzing, B. Schölkopf (2006). Causal Inference by Choosing Graphs with Most Plausible Markov Kernels In: Proceedings of the 9th International Symposium on Artificial Intelligence and Mathematics, Proceedings of the Ninth International Symposium on Artificial Intelligence and Mathematics (AI & Math 2006, 1-11, ISAIM 2006
Talks