I joined DeepMind in April 2019 to work in the machine learning group of Nando de Freitas. Before that, I was a member of EPFL's CVLab since 2014, where I did my PhD supervised by Prof. Pascal Fua and Prof. Raphael Sznitman. In autumn 2017 during my internship at Google Research in Zurich I had a chance to work with Vittorio Ferrari and Jasper Uijlings.
I obtained my M.Sc. degree in Algorithms and Machine Learning from University of Helsinki. During that time, I also worked as a research assistant in the CoSCo group at HIIT. Before, I studied in Russia at the Higher School of Economics in the faculty of Business Informatics and Applied Mathematics.
At DeepMind I work on robotic manipulation tasks from vision with a data-driven approach. We use human annotations to learn reward functions and we use off-policy reinforcement learning to train strategies from historical data. During my PhD I worked on active learning (AL) for different classification tasks. Given a pool of unlabelled data, the goal of AL is to select which data should be annotated in order to learn the model as quickly as possible. Many AL strategies could be proposed, without any of them clearly outperforming others. It led me to meta-learning approach to active learning, where a strategy is learnt from an ensemble of multiple previous AL problems.
September, 2019: Check our new article on data-driven robotics!
April, 2019: I started a new job as a Research Scientist at DeepMind!
January, 2019: We finished work on our new manuscript Discovering General-Purpose Active Learning Strategies with its code.
January, 2019: Our article Geometry in Active Learning for Binary and Multi-class Image Segmentation was published in Computer Vision and Image Understanding journal.
October, 2018: I defended my PhD thesis entitle Learning to Reduce Annotation Load. Youuuhoo! Thanks everyone who supported me during these years!