Contact

Bastian Steudel

Address: Spemannstr. 38
72076 Tübingen
Room number: 215
Phone: +49 7071 601 564
Fax: +49 7071 601 552
E-Mail: bastian.steudel
Print page    
Picture of Steudel, Bastian

Bastian Steudel

Position: Intern  Unit: Alumni Schölkopf

I am part of the Causal and Probabilistic Inference Group and I am working on the problem of inferring causal relations in cases where interventions are infeasible and therefore only data from passive observations is available. It has been argued that causal information can be obtained from statistical conditional independences through the so called Causal Markov and Faithfulness conditions. However, there exist two limitations in this approach. First, inferences can only be drawn in the case of more than two variables. Therefore we are searching for additional assumptions that allow for conclusions already in the two variable case. Second, estimating conditional dependences is challenging if only a limited number of samples are at hand or if samples cannot be obtained under similar experimental conditions (non-i.i.d). We addressed this issue by considering not only statistical but also algorithmic notions of dependences based on the framework of algorithmic information theory. Since the latter rests upon Kolmogorov complexity that is uncomputable we are working on a formal framework for computable alternatives.

Preferences: 
References per page: Year: Medium:

  
Show abstracts

Articles (4):

Janzing D Person, Mooij J Person, Zhang K Person, Lemeire J , Zscheischler J Person, Daniušis P Person, Steudel B Person and Schölkopf B Person (2012) Information-geometric approach to inferring causal directions Artificial Intelligence 182-183 1-31.
Janzing D Person and Steudel B Person (2010) Justifying Additive Noise Model-Based Causal Discovery via Algorithmic Information Theory Open Systems and Information Dynamics 17(2) 189-212.
pdf
Steudel B Person and Ay N (2010) Information-theoretic inference of common ancestors Computing Research Repository (CoRR) abs/1010.5720 18 pages.
Janzing D Person and Steudel B Person (2007) Quantum broadcasting problem in classical low-power signal processing Physical Review A 75(2) 11 pages.

Conference papers (2):

Daniusis P Person, Janzing D Person, Mooij J Person, Zscheischler J Person, Steudel B Person, Zhang K Person and Schölkopf B Person (2010) Inferring deterministic causal relations In: Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, (Ed) P Grünwald and P Spirtes, UAI 2010, AUAI Press, Corvallis, OR, USA, 143-150.
pdf
Steudel B Person, Janzing D Person and Schölkopf B Person (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, OmniPress, Madison, WI, USA, 464-476.
pdf

Export as:
BibTeX, XML, Pubman, Edoc