The spring semester 2021 will certainly take place online until Easter. Exceptions: Courses that can only be carried out with on-site presence. Please note the information provided by the lecturers.

Peter L. Bühlmann: Catalogue data in Spring Semester 2016

Name Prof. Dr. Peter L. Bühlmann
Seminar für Statistik (SfS)
ETH Zürich, HG G 17
Rämistrasse 101
8092 Zürich
Telephone+41 44 632 73 38
Fax+41 44 632 12 28
RelationshipFull Professor

401-3620-16LSeminar in Statistics: Learning Blackjack Restricted registration - show details
Number of participants limited to 18.

Mainly for students from the Mathematics Bachelor and Master Programmes who, in addition to the introductory course unit 401-2604-00L Probability and Statistics, have heard at least one core or elective course in statistics
4 credits2SJ. Peters, P. L. Bühlmann, M. H. Maathuis, N. Meinshausen, S. van de Geer
AbstractIn this seminar, we study different methods that can be applied to the problem of finding a good strategy to play Blackjack. Since the machine does not know the rules of Blackjack, it adopts (and modifies) random strategies. The data for learning will be the games that have been played. Some parts of the seminar will be devoted to implementing these methods in python.
ObjectiveAfter this seminar, you should know
- the problem of reinforcement learning,
- inverse probability weighting and its relation to causality,
- Q-learning,
- contextual multi-armed bandits and
- the optimal strategy of playing BlackJack.
Prerequisites / NoticeWe require at least one course in statistics in addition to the 4th semester course Introduction to Probability and Statistics and basic knowledge in computer programming.

Topics will be assigned during the first meeting.
401-3632-00LComputational Statistics Information 10 credits3V + 2UM. Mächler, P. L. Bühlmann
Abstract"Computational Statistics" deals with modern methods of data analysis (aka "data science") for prediction and inference. An overview of existing methodology is provided and also by the exercises, the student is taught to choose among possible models and about their algorithms and to validate them using graphical methods and simulation based approaches.
ObjectiveGetting to know modern methods of data analysis for prediction and inference.
Learn to choose among possible models and about their algorithms.
Validate them using graphical methods and simulation based approaches.
ContentCourse Synopsis:
multiple regression, nonparametric methods for regression and classification (kernel estimates, smoothing splines, regression and classification trees, additive models, projection pursuit, neural nets, ridging and the lasso, boosting). Problems of interpretation, reliable prediction and the curse of dimensionality are dealt with using resampling, bootstrap and cross validation.
Details are available via .

Exercises will be based on the open-source statistics software R ( Emphasis will be put on applied problems. Active participation in the exercises is strongly recommended.
More details are available via the webpage (-> "Computational Statistics").
Lecture noteslecture notes are available online; see (-> "Computational Statistics").
Literature(see the link above, and the lecture notes)
Prerequisites / NoticeBasic "applied" mathematical calculus and linear algebra.
At least one semester of (basic) probability and statistics.
401-5000-00LZurich Colloquium in Mathematics Information 0 creditsW. Werner, P. L. Bühlmann, M. Burger, S. Mishra, R. Pandharipande, University lecturers
401-5620-00LResearch Seminar on Statistics Information 0 credits2KP. L. Bühlmann, L. Held, T. Hothorn, M. H. Maathuis, N. Meinshausen, S. van de Geer, M. Wolf
AbstractResearch colloquium
401-5640-00LZüKoSt: Seminar on Applied Statistics Information 0 credits1KM. Kalisch, P. L. Bühlmann, R. Furrer, L. Held, T. Hothorn, M. H. Maathuis, M. Mächler, L. Meier, N. Meinshausen, M. Robinson, C. Strobl, S. van de Geer
Abstract5 to 6 talks on applied statistics.
ObjectiveKennenlernen von statistischen Methoden in ihrer Anwendung in verschiedenen Gebieten, besonders in Naturwissenschaft, Technik und Medizin.
ContentIn 5-6 Einzelvorträgen pro Semester werden Methoden der Statistik einzeln oder überblicksartig vorgestellt, oder es werden Probleme und Problemtypen aus einzelnen Anwendungsgebieten besprochen.
3 bis 4 der Vorträge stehen in der Regel unter einem Semesterthema.
Lecture notesBei manchen Vorträgen werden Unterlagen verteilt.
Eine Zusammenfassung ist kurz vor den Vorträgen im Internet unter abrufbar.
Ankündigunen der Vorträge werden auf Wunsch zugesandt.
Prerequisites / NoticeDies ist keine Vorlesung. Es wird keine Prüfung durchgeführt, und es werden keine Kreditpunkte vergeben.
Nach besonderem Programm. Koordinator M. Kalisch, Tel. 044 632 3435
Lehrsprache ist Englisch oder Deutsch je nach ReferentIn.
Course language is English or German and may depend on the speaker.