About the Center

Recent years have proven that the more data is analyzed and the bigger models that analyze them, the better results can be obtained. The breakthrough in Machine Learning came from the successful application of Deep Reparameterized Neural Network, which proved to be an extremely powerful tool when working with huge amounts of data. However, the theoretical foundations of Deep Learning still need more research. As practice has shown, in order to solve complex problems of data analysis, it is necessary to build probabilistic models in which Neural Network will be one of the key elements. The standard tool for building such models is the Bayesian modeling. A striking example of a successful synthesis of the Bayesian approach with Deep Learning are Diffusion Models used to generate various types of data.

The center was created on the basis of the Bayesian Methods Research Group by Dmitry Vetrov in 2017. The center conducts research combining Neural Network and Bayesian Machine Learning Models in the field of Deep Learning, Stochastic Optimization, Tensor expansions and compression of models, Scalable Variational Inference, Diffusion Models, etc.

The head of the Center is Dmitry Vetrov, Ph.D, Research Professor at the Faculty of Computer Science at the National Research University Higher School of Economics, head of the special seminar Bayesian Methods of Machine Learning. Graduated from the Faculty of Computational Mathematics and Cybernetics of Lomonosov Moscow State University. He worked at the Computing Center of the Russian Academy of Sciences, Lomonosov Moscow State University, the Kurchatov Institute, Skoltech, and Yandex. Member of the ELLIS Society (the European Laboratory for Learning and Intelligent Systems).
Developed author's courses Bayesian Methods of Machine Learning,  Graphic Models,  Neurobayesian Models, which he reads at the Faculty of Computer Science (HSE University),  CMC (Lomonosov Moscow State University) and at the Yandex School of Data Analysis. He took part in several interdisciplinary research projects on the development of new methods of Machine Learning and Probabilistic Inference (in cognitive sciences, medicine, inorganic chemistry, etc.).

The author of more than 200 publications, he has repeatedly published at the world's leading conferences on Machine Learning and AI.