Universität Wien

053612 VU Optimisation Methods for Data Science (2021W)

4.00 ECTS (3.00 SWS), SPL 5 - Informatik und Wirtschaftsinformatik
Continuous assessment of course work
MIXED
Moodle

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

max. 25 participants
Language: English

Lecturers

Classes (iCal) - next class is marked with N

  • Monday 04.10. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 07.10. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 11.10. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 14.10. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 18.10. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 21.10. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 25.10. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 28.10. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 04.11. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 08.11. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 11.11. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 15.11. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 18.11. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 22.11. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 25.11. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 29.11. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 02.12. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 06.12. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 09.12. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 13.12. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 16.12. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 10.01. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 13.01. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 17.01. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 20.01. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 24.01. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Thursday 27.01. 11:30 - 12:15 Seminarraum 7, Währinger Straße 29 1.OG
  • Monday 31.01. 09:45 - 11:15 Seminarraum 7, Währinger Straße 29 1.OG

Information

Aims, contents and method of the course

The lecture will be held in presence.
Additionally it will be streamed through a BigBlueButton session as well (see the moodle course). Either way presence is not mandatory, but recommended and I will put the slides online.

This course will give an overview of modern optimization methods, for applications in data science. We will focus on algorithms which scale to large datasets.

Contents:
- Overview of different fields and methods
- the role of convexity
- first order methods, (stochastic) gradient descent
- connection of these methods to related fields
- online optimization
- saddle point problems and games

Assessment and permitted materials

(1) a take-home project
(2) an oral exam at the end of the semester (preferably in person; remotely if necessary)
(3) weekly exercises
(4) bonus points for active participation during classes

Regarding the oral exam: please send me an email so we can arrange a date. Last lecture is on the 31st of January, but I will only talk about previous material / answer questions in this one. So the earliest possible day would be the 25th of January. Preferably I would like to do all the exams between the 1st of February and the 4th of February. If this does not work for you we can arrange something but the latest possible day will be end of February.

Minimum requirements and assessment criteria

Exam: 50%
Project: 25%
Exercises: 25%

Grades:

0-53: nicht genuegend/fail (5)
54-65: genuegend/pass (4)
66-77: befriedigend/satisfactory (3)
78-89: gut/good (2)
90%-100%: sehr gut/excellent (1)

Examination topics

all material covered during the lecture

Reading list

Slides

Optimization for Machine Learning lecture notes by Martin Jaggi EPFL and Bernd Gärtner, ETH
https://raw.githubusercontent.com/epfml/OptML_course/master/lecture_notes/lecture-notes.pdf

Stephen Boyd and Lieven Vandenberghe.
Convex Optimization.
https://web.stanford.edu/~boyd/cvxbook/.

Association in the course directory

Modul: OMD

Last modified: Tu 07.12.2021 15:28