VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

227-0492-00L 1 Credits DR , MSC D-ITET

Statistical Learning Theory: on the sample complexity problem

Lecturers & Examiners: Prof. Dr. Shahar Mendelson

VVZ CR n/a

Last Updated: 2026-02-05 16:29:12

Abstract

The course will be devoted to the solution of a classical question in Statistical Learning Theory: identifying the optimal sample complexity (with respect to the squared loss) under minimal assumptions. The main ngredients are elements of the small-ball method and the notion of median-of-means tournaments - with one additional application: an optimal mean estimation procedure for random vectors.

General Information

Language: English
Levels: DR , MSC
Frequency: Yearly recurring

Examination

Type: ungraded semester performance

Course Components

Type	Title	Time & Place	Hours
seminar	Statistical Learning Theory: on the sample complexity problem The first two meetings are scheduled for 2 Oct and 16 Oct, (1415-1600). The dates for the rest of the course will be decided then.	02.10 Date 14:15-16:00 (HG D 7.2) 16.10 Date 14:15-16:00 (HG F 26.1) 30.10 Date 14:15-16:00 (ML H 43) 13.11 Date 14:15-16:00 (ML H 43) 04.12 Date 14:15-16:00 (ML J 37.1) 18.12 Date 14:15-16:00 (ML J 37.1) 08.01 Date 14:15-16:00 (ML J 37.1) 15.01 Date 14:15-16:00 (ETZ F 91) 29.01 Date 14:15-16:00 (ML J 37.1) 10.02 Date 14:15-16:00 (ML J 37.1) 12.02 Date 14:15-16:00 (ML J 37.1) 19.02 Date 14:15-16:00 (ML H 37.1)	25 h semesterly

Offered In

Electrical Engineering and Information Technology Master
- Master Studies (Programme Regulations 2018)
  - Track: Signal Processing and Machine Learning (The core courses and specialisation courses below are a selection for students who wish to specialise in the area of "Signal Processing and Machine Learning ", see . The individual study plan is subject to the tutor's approval.)
    - Specialisation Courses (These specialisation courses are particularly recommended for the area of "Signal Processing and Machine Learning", but you are free to choose courses from any other field in agreement with your tutor. A minimum of 40 credits must be obtained from specialisation courses during the MSc EEIT.)
- Master Studies (Programme Regulations 2008)
  - Major Courses (A total of 42 CP must be achieved during the Master Programme. The individual study plan is subject to the tutor's approval.)
    - Signal Processing and Machine Learning
      - Recommended Subjects
Doctorate Information Technology and Electrical Engineering (A minimum of 12 ECTS credit points must be obtained during doctoral studies (also see sub-categories for details) More Information at )
- Subject Specialisation (The courses on offer below are only a small selection out of a much larger available number of courses. Please discuss your course selection with your PhD supervisor.)