Ilya V. Schurov

Ilya V. Schurov

Mathematics, ML & AI

Omnifold

About me

I’m a mathematician, ML researcher, and technology enthusiast. I love pure mathematics, and I equally enjoy coding and solving applied problems. This dual passion allows me to contribute meaningfully across disciplines, in both academia and industry.

Currently, I work at Omnifold, where we use AI and mathematical modeling for forecasting and optimization. Previously, I was a researcher at Radboud University and an associate professor at HSE University, working on projects spanning differential equations, physics, game theory, biology, and linguistics.

I’ve taught university courses on calculus, machine learning, differential equations, and data science. I also created several online courses for Coursera on the foundations of machine learning and authored free interactive textbooks on calculus and ordinary differential equations, used by thousands of Russian-speaking students.

Download my CV.

Interests
  • Machine Learning
  • Differential Equations
  • Dynamical Systems
Education
  • Ph.D. in Mathematics, 2010

    Moscow State University

  • M.S. in Mathematics, 2006

    Moscow State University

Textbooks

I want to reinvent mathematical textbooks: make them accessible, friendly, full of illustrations and in-depth explanations of the essence of mathematical concepts. To achieve this goal, I even developed my own publishing platform that leverages modern web-technologies and allows to include interactive elements to mathematical texts.

Calculus
Friendly introduction to rigorous one-dimensional calculus. We have precise epsilon-delta definitions and all the proofs, carefully explained, with examples, motivations and illustrations. Batteries included!
Ordinary differential equations
Introductory textbook with focus on important geometrical and dynamical phenomena like conservation laws, stability and bifurcations.

Research Papers

(2024). Long range segmentation of prokaryotic genomes by gene age and functionality. Nucleic Acids Research.

Cite DOI URL

(2024). Invariant multiscale neural networks for data-scarce scientific applications.

Cite arXiv URL

(2022). Can Recall Data Be Trusted?. Field Methods, 34 (4), 2022.

Cite DOI Code

(2020). Bachet’s game with lottery moves. Discrete Mathematics, 343 (4), 111704.

Cite DOI arXiv