Calculated based on number of publications stored in Pure and citations from Scopus

Research activity per year

If you made any changes in Pure these will be visible here soon.

Personal profile

Research interests

Dmitry graduated from the Department of Mechanics and Mathematics of Moscow State University in 1998, where he also obtained his Candidate of Sciences degree in 2002. Later on, he worked at the Institute for Information Transmission Problems (IITP), Dublin Institute for Advanced Studies, and Munich University. In 2015, he obtained his Doctor of Sciences degree from IITP.

Dmitry’s interests cover a wide range of topics in Applied Mathematics. He started his research career with studies of stochastic processes and quantum lattice systems, gradually shifting to topics related to engineering, data analysis, and optimization.

Academic Reputation and Societal Impact

Had 200+ citations in Google Scholar;  

Received multiple (10+) requests to referee submissions to top journals and conferences in applied mathematics and machine learning (Annals of Statistics, Neural networks, Constructive Approximation, JMLR, ICML);

Was invited as a speaker/participant to several regional events/seminars and international conferences/workshops in machine learning;

Established contacts with Moscow research office of Huawei in the domain of applications of machine learning to wireless communication and AI. Participated in one Skoltech-Huawei project and initiated another (see item IV(a)) ;

Was the team lead in the machine learning part of the pregnancy loss SBI project (see item IV(a)). Initiated a new research direction – genotype-to-phenotype prediction using UK Biobank data;

Obtained access to the UK Biobank dataset (uploaded to Zhores cluster). Access is granted for the period of 3 years starting from April 2018. The dataset is the world’s largest collection of human genetic and phenotypic data (500000 people). Only a few teams in Russia have access to this dataset. We are using the dataset to construct accurate genotype-to-phenotype predictive models based on modern machine learning methods. This is a central problem in modern human genetics that can potentially have important applications to automated decease diagnostics.


Dive into the research topics where Dmitry Yarotskiy is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
  • 1 Similar Profiles


Recent external collaboration on country/territory level. Dive into details by clicking on the dots or