=Paper=
{{Paper
|id=Vol-1649/2
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-1649/2.pdf
|volume=Vol-1649
}}
==None==
<pdf width="1500px">https://ceur-ws.org/Vol-1649/2.pdf</pdf>
<pre>
ITAT 2016 Proceedings, CEUR Workshop Proceedings Vol. 1649, p. 2
http://ceur-ws.org/Vol-1649, Series ISSN 1613-0073, c 2016 M. Valko


                         Sequential Learning on Graphs With Limited Feedback
                                             (Invited Talk)

                                                                Michal Valko

                                                      INRIA Lille – Nord Europe, France
                                                         michal.valko@inria.fr

       In this talk, we investigate the structural properties of certain sequential decision-making problems with limited feedback
       (bandits) in order to bring the known algorithmic solutions closer to a practical use including, online influence maximiza-
       tion or sequential recommender systems. To address these structured settings, we can always ignore the graph and use
       known algorithms for multi-armed bandits. However, their performance scales unfavorably with the number of nodes
       N, which is undesirable when N means a thousand of sensors or a million of movies. We describe several graph bandit
       problems and show how to use their graph structure to design new algorithms with faster learning rates, scaling not with
       N but with graph-dependent quantities, often much smaller than N in real-world graphs.

          Michal Valko absolvoval magisterské štúdium informatiky na FMFI UK v Bratislave, doktorandské štúdium ukončil na
       University of Pittsburgh v oblasti machine learning a habilitáciu v sequential machine learning obhájil na École Normale
       Supérieure de Cachan. Od roku 2011 pôsobí ako vedecký pracovník v tíme SequeL na Francúzskom národnom inštitúte pre
       informatiku a aplikovanú matematiku - Inria. Hlavnou oblast’ou jeho výskumu je machine learning, kde sa špecializuje
       na metódy, ktoré minimalizujú objem dát, ktoré treba poskytnút’ algoritmom predtým, než začnú byt’ užitočné.

</pre>