Biography
Nikita Doikov will join Cornell in January 2026 as an Assistant Professor in the School of Operations Research and Information Engineering. He received his PhD from UCLouvain, Belgium, under the supervision of Yurii Nesterov in 2021. After that, he was a postdoctoral researcher at EPFL, Switzerland, working in the Machine Learning and Optimization Laboratory led by Martin Jaggi. He also gained industrial experience as an intern at Google in 2016 and 2018.
Research Interests
His research is in optimization algorithms and their applications in machine learning and AI. In particular, he focuses on provably efficient methods that exploit problem structure, such as second-order information, model landscapes, and stochasticity, as well as on utilizing scalable decentralized architectures to accelerate model training.
Select Publications
-
Nikita Doikov. “Minimizing Quasi-Self-Concordant Functions by Gradient Regularization of Newton Method” Mathematical Programming (2025)
-
Nikita Doikov. “Lower Complexity Bounds for Minimizing Regularized Functions” Optimization Letters (2025)
-
Nikita Doikov, Sebastian U. Stich, Martin Jaggi. “Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions” International Conference on Machine Learning (2024)
-
Nikita Doikov, Yurii Nesterov. “Local convergence of tensor methods” Mathematical Programming (2021)
-
Nikita Doikov, Yurii Nesterov. “Contracting Proximal Methods for Smooth Convex Optimization” SIAM Journal on Optimization (2020)
Education
- Ph.D. (Engineering and Technology), UCLouvain 2021
- M.S. (Applied Mathematics and Informatics), Higher School of Economics 2017
- B.S. (Applied Mathematics and Computer Science), Lomonosov Moscow State University 2015