

First-order and online optimization methods
- Lecturer: Katerina Papagiannouli, André Uschmajew
- Date: Lectures: Tuesdays 11:00-12:30, Exercises (biweekly): Tuesdays 14:00-15:00
- Room: MPI MiS G3 10
- Keywords: online convex optimization, optimization on manifolds, multi-armed bandit, games and saddle point problems
- Prerequisites: Basics of linear algebra, analysis, and probability
- Remarks: The class will start on 19/04; 9-12 lectures
Abstract
In this class we will study first-order optimization methods for constrained and unconstrained optimization methods. In addition, a major part of the lecture will be devoted to aspects of online convex optimization, which is a combination of convex optimization, statistical learning, and game theory. Online optimization is motivated from practical applications in which the environment is so complex that it is difficult to design robust optimization models and apply classic algorithmic theory. In the online optimization framework, the optimization is instead considered as a process that learns from experience as one goes along and more aspects of the problem are observed. In the exercise class (on demand) a practical application to recommender systems will be considered.To keep informed about changes to this lecture subscribe to lecture mailinglist
Important information
- Due to the pandemic, it is strongly recommended to register for a lecture series before attending one of the lectures. For this registration, we simply use the mailing list for the lecture series. So, if you plan to attend a lecture (series), please subscribe the mailing list which is linked below the respective lecture.
- Obviously, this rule is only valid for in-person lectures. However, even for the online events it might be a good idea to subscribe. This way, you will receive the information on how to attend the online meetings.
Regular lectures: Summer semester 2022
- Representation theory of finite groups
- Arthur Bik
- Thursdays 7:30-9:00 and Fridays 9:15-10:45, SG 3-10
- To keep informed about changes to this lecture subscribe to lecture mailinglist
- Bielefeld-Leipzig online seminar: Mathematics of Machine Learning
- Benjamin Gess
- Wednesdays 16:15-17:45, Videobroadcast
- Mathematical methods in biology and neurobiology
- Jürgen Jost
- Friday, 14.00, MPI MiS E1 05 (Leibniz)
- To keep informed about changes to this lecture subscribe to lecture mailinglist
- Tropical Probability Theory
- Rostislav Matveev
- Wednesday, 11.00-12.30, MPI MiS A3 02
- To keep informed about changes to this lecture subscribe to lecture mailinglist
- Non-backtracking operators of graphs
- Raffaella Mulas, Leo Torres
- Mondays at 3pm, starting May 2, MPI MiS A3 01
- To keep informed about changes to this lecture subscribe to lecture mailinglist
- Recent developments in discrete Ricci curvature
- Florentin Münch
- Wednesday, 15.00, MPI MiS A3 01
- To keep informed about changes to this lecture subscribe to lecture mailinglist
- First-order and online optimization methods
- Katerina Papagiannouli, André Uschmajew
- Lectures: Tuesdays 11:00-12:30, Exercises (biweekly): Tuesdays 14:00-15:00, MPI MiS G3 10
- To keep informed about changes to this lecture subscribe to lecture mailinglist
- Spin Glasses
- Tobias Ried
- tba, Videobroadcast
- To keep informed about changes to this lecture subscribe to lecture mailinglist
- IMPRS Ringvorlesung
- Lecturers: Bernd Rosenow, Felix Otto, Sayan Mukherjee
- Date: usually Thursdays (starting 7.4.2022), 9.15 - 10.45, see schedule for divergent dates and times and more info
- Room: MPI MiS, Leibniz-Hörsaal, also hybrid
- To keep informed about changes to this lecture subscribe to lecture mailinglist
Access Information (presence lectures only)
External guests please use the main entry Inselstr. 22 and go to the 3rd. floor (reception, see the map). All other doors are closed.