Marina Sheshukova
- Junior Research Fellow: Faculty of Computer Science / AI and Digital Science Institute / International Laboratory of Stochastic Algorithms and High-Dimensional Inference
- Lecturer: Faculty of Computer Science / Big Data and Information Retrieval School
- Marina Sheshukova has been at HSE University since 2021.
Education
2023
Bachelor's in Applied Mathematics and Information ScienceHSE University
Courses (2026/2027)
- Markov Chains (Master’s programme; Faculty of Computer Science field of study Applied Mathematics and Informatics; 1 year, 2 module)Eng
- Markov Chains (Mago-Lego; Faculty of Computer Science; 2 module)Eng
- Mentor's Seminar "Math of Machine Learning " (Master’s programme; Faculty of Computer Science field of study Applied Mathematics and Informatics; 2 year, 1-3 module)Eng
- Sampling and Generative Modeling (Master’s programme; Faculty of Computer Science field of study Applied Mathematics and Informatics; 1 year, 3 module)Eng
- Sampling and Generative Modeling (Mago-Lego; Faculty of Computer Science; 3 module)Eng
- Past Courses
Courses (2025/2026)
- Advanced Statistics 2 (Bachelor’s programme; Faculty of Computer Science field of study Applied Mathematics and Information Science; 3 year, 1, 2 module)Rus
- Advanced Statistics 2 (Bachelor’s programme; Faculty of Computer Science field of study Applied Mathematics and Information Science; 3 year, 1, 2 module)Rus
- Markov Chains (Mago-Lego; Faculty of Computer Science; 2 module)Eng
- Markov Chains (Master’s programme; Faculty of Computer Science field of study Applied Mathematics and Informatics; 1 year, 2 module)Eng
- Mathematical Statistics 1 (advanced course) (Bachelor’s programme; Faculty of Computer Science field of study Applied Mathematics and Information Science; 2 year, 4 module)Rus
- Mentor's Seminar "Math of Machine Learning " (Master’s programme; Faculty of Computer Science field of study Applied Mathematics and Informatics; 2 year, 1-3 module)Eng
- Sampling and Generative Modeling (Mago-Lego; Faculty of Computer Science; 3 module)Eng
- Sampling and Generative Modeling (Master’s programme; Faculty of Computer Science field of study Applied Mathematics and Informatics; 1 year, 3 module)Eng
Courses (2024/2025)
- Mathematical Statistics 1 (advanced course) (Bachelor’s programme; Faculty of Computer Science field of study Applied Mathematics and Information Science; 2 year, 4 module)Rus
20
Jul
2026
Scientists Propose Method for More Efficient Resource Use in Machine Learning
An international group of researchers, including mathematicians from the AI and Digital Science Institute at the HSE Faculty of Computer Science, has provided a theoretical justification for a simple and computationally efficient method of estimating uncertainty in Stochastic Gradient Descent (SGD). The paper has been published on the scientific preprint server arXiv.org and presented at AISTATS 2026.