Alexey has expertise in numerical methods, statistics and industrial applications of data analysis. In 2012, Alexey graduated from the Department of Control and Applied Mathematics of Moscow Institute of Physics and Technology (MIPT). In his Master’s thesis Alexey proposed a modification of Bayesian approach for linear regression that allows an automated feature selection. He then completed a PhD in Math at IITP RAS. Alexey obtained a new result on effectiveness of Bayesian procedures for Gaussian process regression and a first ever theoretical justification for selection of design of experiments for variable fidelity models as well as minimax errors for Gaussian process regression. His research was published in a number of peer-reviewed journals and top-ranked conferences such as AISTATS.
During his studies at MIPT Alexey joined a Skolkovo resident company DATADVANCE and took part in the development of MACROS library dedicated to data analysis for engineers. He developed a first ever industry-level tool for data fusion that solves a regression problem for the case of data with more than one fidelity. Alexey also completed a number of projects connected with application of data analysis in industry for such companies as AREVA, TOTAL and Airbus.
Now Alexey focuses his research on the development of a new generation of methods for processing of molecular modeling data using Machine Learning. He also actively participates in industrial projects and teaching routines including joint projects with Sberbank and Gazprom Neft.
Development of advanced algorithms for battery health optimization and prediction
A. Zaytsev, E. Burnaev. Large scale variable fidelity surrogate modeling. Annals of Mathematics and Artificial Intelligence, 81: 167-186. 2017. https://link.springer.com/article/10.1007/s10472-017-9545-y
A. Zaytsev, E. Burnaev. Minimax Approach to Variable Fidelity Data Interpolation. Artificial Intelligence and Statistics, 652-661. 2017. http://proceedings.mlr.press/v54/zaytsev17a.html
A. Zaytsev. Variable Fidelity Regression Using Low Fidelity Function Blackbox and Sparsification. Symposium on Conformal and Probabilistic Prediction with Applications, 147-164. 2016. https://link.springer.com/chapter/10.1007/978-3-319-33395-3_11
A. Zaytsev. Reliable surrogate modeling of engineering data with more than two levels of fidelity. Mechanical and Aerospace Engineering (ICMAE), 2016 7th International Conference. 2016. ieeexplore.ieee.org/abstract/document/7549563/
A.A Zaitsev, E.V. Burnaev, V.G. Spokoiny. Properties of the posterior distribution of a regression model based on Gaussian random fields. Automation and Remote Control 74 (10), 1645-1655, 2013. link.springer.com/article/10.1134/S0005117913100056
E.V. Burnaev, A.A. Zaytsev, V.G. Spokoiny (alphabetic order of authors). The Bernstein-von Mises theorem for regression based on Gaussian Processes. Russ. Math. Surv 68 (5), 954-956, 2013. iopscience.iop.org/article/10.1070/RM2013v068n05ABEH004863
E.V. Burnaev, M.E. Panov, A.A. Zaytsev. Regression on the basis of nonstationary Gaussian processes with Bayesian regularization. Journal of Communications Technology & Electronics 61 (6), 661. 2016. https://link.springer.com/article/10.1134/S1064226916060061
E.V. Burnaev, A.A. Zaytsev. Surrogate modeling of multifidelity data for large samples. Journal of Communications Technology & Electronics 60 (12), 1348. 2015. link.springer.com/article/10.1134/S1064226915120037
A.A. Zaytsev, E.V. Burnaev, V.G. Spokoiny. Properties of the Bayesian parameter estimation of a regression based on Gaussian processes. J. Math. Sci 203 (6), 789-798. 2014. https://www.datadvance.net/assets/files/publications/zaytsev13fam.pdf
N. Kozlovskaya, A. Zaytsev. Deep Ensembles for Imbalanced Classification. Accepted to ICMLA. 2017
Masters in Math at MIPT
PhD in Statistics and Machine Learning at IITP RAS