I am a PhD Student doing research in Deep Learning at Constructor University, Bremen. I am studying fundamental properties of neural networks, such as the structure of loss landscape, what patterns do neural networks learn during training, how to train models generalizing well to test data, why ensembles of neural networks lead to quality improvement, and so on. I am also interested in the area of knowledge transfer, including self-supervised learning and transfer learning.

I am pleased to be a part of Bayesian Methods Research Group (a.k.a. Bayesgroup) and work under the supervision of Dmitry Vetrov and Ekaterina Lobacheva. I have completed both BSc and MSc degrees at the Faculty of Computer Science at HSE University. I also enjoy teaching courses about Machine Leaning and Deep Learning.

News

8 March 2024 » Our NeurIPS-2023 paper is presented at ML Collective paper reading group!
6 February 2024 » Moving to Constructor University in Bremen, Germany