| Associate Professor (Ingenuity New Faculty) Department of Computing Science University of Alberta Edmonton, Alberta Canada T6G 2E8 |
Office: 311 Athabasca Hall Email: szepesva AT cs DOT ualberta DOT ca Phone: (780) 492-8581 Fax: (780) 492-1071 |
[en/hu dict] [RLFA RG] [CMPUT 412] [calendar] [math genealogy] |
Who am I?
|
Professionally: Faculty at the Department of Computing Science
and a PI at
AICML.
Member of RLAI. On leave from SZTAKI. My old homepage there.
Personally: Husband of my lovely wife
Beáta
and proud dad of
Dávid,
Réka,
Eszter and
Csongor. |
|
News
|
CMPUT 412 class final project demo video by Eszter and Reka. |
- In Fall 2009 I was teaching On-line learning.
- Participating in the "Subspace methods for system identification" reading group discussing this book. -->
- Participating in the "Beyond Lasso" reading group
- Organizing the On-line Learning with Limited Feedback
workshop to be held at COLT-09,
June 18, Montreal, Canada.
- I was a PC member of ALT-09: You should consider going to ALT-09. Reasons to go: Excellent set of invited speakers, organizers and PC Plus: Porto in October can be beautiful, not talking about the famous Port wine!
- I enjoyed participating in Max Planck Symposium on Autonomous Systems in Tübingen.
- I have graduated my first students at UofA!
- The Compressive sensing reading group was functional during 2008 Fall.
- I gave some talks at MLSS'08, Ile de Re:
- I co-organized the ICML/COLT/UAI-08 workshop `Machine Learning for Health-Care Applications' with Milos Hauskrecht and Dale Schuurmans. Come and join us in Helsinki!
- I talked at MLSS'08 (Kioloa) on "Reinforcement Learning". Topics covered: MDPs, dynamic programming - the operator-theoretic approach, (approximate) planning algorithms and the curse of dimensionality, efficient on-line learning, classical and new algorithms (TD and least-squares algorithms).
- My slides on batch RL presented at the
RL Workshop in Barbados.
I gave a summary of what is known (theoretically) and listed ca. 10 open questions. If you are interested in any of these problems, drop me an e-mail!
Research topics
- What makes learning possible with a "few" examples?
- How to let machines learn to make good decisions?
My publications should tell you more.
