lunduniversity.lu.se

Automatic Control

LTH best Master's thesis

Johanna Wilroth has been awarded the prize "LTHs Jubileumsstipendium 2020" for the best master thesis at LTH. In her thesis "Domain Adaptation for Attention Steering," Wilroth studied novel algorithms for improving the performance of hearing aids using EEG signals in combination with auditory input. The master thesis was done at the Department of Automatic Control, with Carolina Bergeling as main supervisor, in collaboration with the research center Eriksholm/Oticon in Denmark. The collaboration also involved the departments of Psychology and Mathematical Statistics at Lund University.

 

Seminar by Yassir Jedra: Minimal Expected Regret for the Online LQR Problem

Seminarium

From: 2021-09-15 11:00 to 12:00
Place: Seminar Room KC 3N27
Contact: anders [dot] rantzer [at] control [dot] lth [dot] se
Save event to your calendar


Abstract:
Recently, there has been a surge of interest in studying the Linear
Quadratic Regulator (LQR) problem within the online learning community.
One of the main goals often considered  by this community is to devise
learning algorithms and study their so-called regret. In this talk, I
will attempt to provide a comprehensive discussion on recent work on the
LQR problem from the online learning community. I will also present some
of our recent work on this topic where we devise a new learning
algorithm and provide guarantees on its expected regret. I will further
highlight the many desirable properties that our algorithm enjoys in
contrast with existing ones, notably from an algorithm design
perspective, where we allow our algorithm to update its policy
continuously. On a technical level, achieving a simple algorithm while
retaining strong regret guarantees poses serious challenges. We are able
to tackle these challenges by carefully leveraging recent tools from
random matrix theory and self-normalized processes.


Presented by Yassir Jedra from the Division of Decision and Control Systems at KTH



Recent Publications