Nicolai Meinshausen: Catalogue data in Spring Semester 2019
|Name||Prof. Dr. Nicolai Meinshausen|
Professur für Statistik
ETH Zürich, HG G 24.2
|Telephone||+41 44 632 32 74|
|401-3620-19L||Student Seminar in Statistics: Adversarial and Robust Machine Learning |
Number of participants limited to 22.
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. Also offered in the Master Programmes Statistics resp. Data Science.
|4 credits||2S||P. L. Bühlmann, M. H. Maathuis, N. Meinshausen, S. van de Geer|
|Abstract||As statistical and machine learning models are increasingly employed in many real-world applications it becomes more important to understand the vulnerabilities and robustness properties of these models.|
In the first part of this seminar, we will study papers relating to adversarial examples. In the second part of the course, we will review other types of distribution shifts.
|Objective||After this seminar, you should know|
- properties of adversarial examples
- some attacks and defenses
- some concepts from robust optimization and distributional robustness
- other distribution shifts that can fool machine learning models in general and neural networks in particular
|Content||As statistical and machine learning models are increasingly employed in many real-world applications it becomes more important to understand the vulnerabilities and robustness properties of these models. In the first part of this seminar, we will study papers relating to adversarial examples, covering their properties, various attacks and defenses. In the second part of the course, we will review other types of distribution shifts, posing significant challenges for state-of-the-art machine learning models. Some parts of the seminar will be devoted to implementing these methods in python.|
|Prerequisites / Notice||We require at least one course in statistics or machine learning and basic knowledge in computer programming. Some background knowledge in deep learning is helpful but not strictly required.|
Topics will be assigned during the first meeting.
|401-4620-00L||Statistics Lab |
Number of participants limited to 27.
|6 credits||2S||M. Kalisch, M. H. Maathuis, M. Mächler, L. Meier, N. Meinshausen|
|Abstract||"Statistics Lab" is an Applied Statistics Workshop in Data Analysis. It|
provides a learning environment in a realistic setting.
Students lead a regular consulting session at the Seminar für Statistik
(SfS). After the session, the statistical data analysis is carried out and
a written report and results are presented to the client. The project is
also presented in the course's seminar.
|Objective||- gain initial experience in the consultancy process |
- carry out a consultancy session and produce a report
- apply theoretical knowledge to an applied problem
After the course, students will have practical knowledge about statistical
consulting. They will have determined the scientific problem and its
context, enquired the design of the experiment or data collection, and
selected the appropriate methods to tackle the problem. They will have
deepened their statistical knowledge, and applied their theoretical
knowledge to the problem. They will have gathered experience in explaining
the relevant mathematical and software issues to a client. They will have
performed a statistical analysis using R (or SPSS). They improve their
skills in writing a report and presenting statistical issues in a talk.
|Content||Students participate in consulting meetings at the SfS. Several consulting|
dates are available for student participation. These are arranged
-During the first meeting the student mainly observes and participates in
the discussion. During the second meeting (with a different client), the
student leads the meeting. The member of the consulting team is overseeing
(and contributing to) the meeting.
-After the meeting, the student performs the recommended analysis, produces
a report and presents the results to the client.
-Finally, the student presents the case in the weekly course seminar in a
talk. All students are required to attend the seminar regularly.
|Literature||The required literature will depend on the specific statistical problem|
under investigation. Some introductory material can be found below.
|Prerequisites / Notice||Prerequisites: |
Sound knowledge in basic statistical methods, especially regression and, if
possible, analysis of variance. Basic experience in Data Analysis with R.
|401-5620-00L||Research Seminar on Statistics||0 credits||2K||P. L. Bühlmann, L. Held, T. Hothorn, D. Kozbur, M. H. Maathuis, N. Meinshausen, S. van de Geer, M. Wolf|
|401-5640-00L||ZüKoSt: Seminar on Applied Statistics||0 credits||1K||M. 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|
|Abstract||5 to 6 talks on applied statistics.|
|Objective||Kennenlernen von statistischen Methoden in ihrer Anwendung in verschiedenen Gebieten, besonders in Naturwissenschaft, Technik und Medizin.|
|Content||In 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 notes||Bei manchen Vorträgen werden Unterlagen verteilt. |
Eine Zusammenfassung ist kurz vor den Vorträgen im Internet unter http://stat.ethz.ch/talks/zukost abrufbar.
Ankündigunen der Vorträge werden auf Wunsch zugesandt.
|Prerequisites / Notice||Dies 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.
|401-5680-00L||Foundations of Data Science Seminar||0 credits||P. L. Bühlmann, H. Bölcskei, J. M. Buhmann, T. Hofmann, A. Krause, A. Lapidoth, H.‑A. Loeliger, M. H. Maathuis, N. Meinshausen, G. Rätsch, S. van de Geer|
|401-6102-00L||Multivariate Statistics||4 credits||2G||N. Meinshausen|
|Abstract||Multivariate Statistics deals with joint distributions of several random variables. This course introduces the basic concepts and provides an overview over classical and modern methods of multivariate statistics. We will consider the theory behind the methods as well as their applications.|
|Objective||After the course, you should be able to:|
- describe the various methods and the concepts and theory behind them
- identify adequate methods for a given statistical problem
- use the statistical software "R" to efficiently apply these methods
- interpret the output of these methods
|Content||Visualization / Principal component analysis / Multidimensional scaling / The multivariate Normal distribution / Factor analysis / Supervised learning / Cluster analysis|
|Literature||The course will be based on class notes and books that are available electronically via the ETH library.|
|Prerequisites / Notice||Target audience: This course is the more theoretical version of "Applied Multivariate Statistics" (401-0102-00L) and is targeted at students with a math background. |
Prerequisite: A basic course in probability and statistics.
Note: The courses 401-0102-00L and 401-6102-00L are mutually exclusive. You may register for at most one of these two course units.