Michal Valko
search externally:   Google Scholar,   Springer,   CiteSeer,   Microsoft Academic Search,   Scirus ,   DBlife


Michal is a junior scientist in SequeL team at INRIA Lille - Nord Europe, France, lead by Philippe Preux and Remi Munos. He works with Remi Munos, Mohammad Ghavamzadeh, Alessandro Lazaric, and Daniil Ryabko. Michal is primarily interested in designing algorithms that would require as little human supervision as possible. This means 1) reducing the “intelligence” that humans need to input into the system and 2) minimising the data that humans need spend inspecting, classifying, or “tuning” the algorithms. Moreover, the important feature of machine learning algorithms should be the adaptation to changing environments. That is why he is working in domains that are able to deal with minimal feedback, such as semi-supervised learning, bandit algorithms, and anomaly detection. The common thread of Michal's work has been adaptive graph-based learning and its application to the real world applications such as medical error detection and face recognition. He received his PhD in 2011 from University of Pittsburgh under the supervision of Miloš Hauskrecht and after was a postdoc of Remi Munos.


flag Learning from a Few labels and a Stream of Unlabeled Data
as author at  Large-scale Online Learning and Decision Making (LSOLDM) Workshop, Cumberland Lodge 2012,