Professor: Ivan Oseledets
Graduated from: MIPT, Skoltech
Research interests: Stochastic Optimization, Machine Learning, Deep Learning
Thesis title: Matrix methods in stochastic optimization
Publications: Merkulov, D., & Oseledets, I. (2019). Empirical study of extreme overfitting points of neural networks. arXiv preprint arXiv:1906.06295.
Conferences: “From splitting scheme to stochastic optimization” D.Merkulov, I. Oseledets, 5th International Conference on Matrix Methods in Mathematics and applications (MMMA-2019)
Developing theoretical foundations of Deep Neural Networks and their applications
Head of Research Group on Signal Processing