I am a first year PhD student at Moscow Institute of Physics and Technology, Phystech School of Applied Mathematics and Informatics. I work under supervision of professor Alexander Gasnikov. My research interests include Stochastic Optimization, Distibuted Optimization and their applications to Machine and Deep Learning.
anbeznosikov@gmail.com
beznosikov.an@phystech.edu
Operating systems:
Mac OSX, Linux, Microsoft Windows
Programming languages:
Python, LaTeX, SQL, C, C#
Russian (native)
English (upper intermediate)
Basketball
Tennis
Sep 2016 - Aug 2020
Phystech School of Applied Mathematics and Informatics/Department of Control and Applied Mathematics
Thesis (in Russian): Distributed decentralized gradient-free methods for solving non-smooth stochastic convex optimization problems
Advisor: Alexander Gasnikov
Sep 2020 - Aug 2022
Phystech School of Applied Mathematics and Informatics
Thesis: Methods for solving distributed saddle point problems:
lower bounds, optimal and practical algorithms
Advisor: Alexander Gasnikov
Sep 2022 - Now
Phystech School of Applied Mathematics and Informatics
Sep 2017 - Now
Teaching assistant for the following courses: Stochastic Process, Probability Theory, Discrete Analysis, Databases.
Feb 2021 - Now
Teaching assistant.
Feb 2021 - Now
Research assistant. Heads: Eric Moulines, Alexey Naumov.
Mar 2021 - Now
Junior Researcher. Head: Andrei Raigorodskii.
Jul 2021 - Now
Research intern in the Yandex Research team.
Sep 2022 - Now
Researcher. Head: Alexander Gasnikov
Oct 2022 - Now
Leading expert
Jan 2023 - Now
Laboratory head
In the new semester I teach the Stochastic Process and Numerical Optimization courses in MIPT as a seminar teacher. Also I am a co-lecturer of "Optimization in Machine Learning" course in VK Academy.
Feb 6, 2023
We have 1 paper at the main conference (poster):
Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods (with Eduard Gorbunov, Hugo Berard and Nicolas Loizou) - arxiv
Jan 20, 2023
We have 4 papers at the main conference (posters). These papers are
1) Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity (with Dmitry Kovalev, Ekaterina Borodich, Gesualdo Scutari, Alexander Gasnikov) - arxiv
2) Optimal Algorithms for Decentralized Stochastic Variational Inequalities (with Dmitry Kovalev, Abdurakhmon Sadiev, Michael Persiianov, Peter Richtárik, Alexander Gasnikov) - arxiv
3) Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees (with Peter Richtárik, Michael Diskin, Max Ryabinin, Alexander Gasnikov) - arxiv
4) Decentralized Local Stochastic Extra-Gradient for Variational Inequalities (with Pavel Dvurechensky, Anastasia Koloskova, Valentin Samokhin, Sebastian U Stich, Alexander Gasnikov) - arxiv
Sep 15, 2022
