website templates

Posts

Mobirise

Master thesis defence

On 14 June I had a master thesis defence at MIPT.

June 14, 2022

Mobirise

ICML: 1 accepted paper

We have one paper at the main conference:

The Power of First-Order Smooth Optimization for Black-Box Non-Smooth Problems (Alexander Gasnikov, Anton Novitskii, Vasilii Novitskii, Farshed Abdukhakimov, Dmitry Kamzolov, Aleksandr Beznosikov, Martin Takáč, Pavel Dvurechensky, Bin Gu) - main conference (short talk) - arxiv

Jun 13, 2022

Mobirise

New paper out

"Stochastic Gradient Methods with Preconditioned Updates" - joint work with Abdurakhmon Sadiev, Abdulla Jasem Almansoori, Dmitry Kamzolov, Rachael Tappenden, Martin Takáč.

June 1, 2022

Mobirise

New paper out

"Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity" - joint work with Dmitry Kovalev, Ekaterina Borodich, Alexander Gasnikov, Gesualdo Scutari.

May 30, 2022

Mobirise

New paper out

Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods" - joint work with Eduard Gorbunov, Hugo Berard and Nicolas Loizou.

Feb 15, 2022

Mobirise

New paper out

"Optimal Algorithms for Decentralized Stochastic Variational Inequalities" - joint work with Dmitry Kovalev, Abdurakhmon Sadiev, Michael Persiianov, Peter Richtárik and Alexander Gasnikov.

Feb 6, 2022

Mobirise

Teacher on the Stochastic Processes course

In the new semester I begin to teach the Stochastic Processes course in MIPT as a seminar teacher (lecturer: Maksim Shirobokov).

Feb 1, 2022

Mobirise

New paper out

"The Power of First-Order Smooth Optimization for Black-Box Non-Smooth Problems" - joint work with Alexander Gasnikov, Anton Novitskii, Vasilii Novitskii, Farshed Abdukhakimov, Dmitry Kamzolov, Martin Takáč, Pavel Dvurechensky and Bin Gu.

Jan 28, 2022

Mobirise

New paper out

"A Unified Analysis of Variational Inequality Methods: Variance Reduction, Sampling, Quantization and Coordinate Descent" - joint work with Alexander Gasnikov, Karina Zainulina, Alexander Maslovskiy and Dmitry Pasechnyuk.

Jan 28, 2022

Mobirise

Grant for young researchers

Our team: Eduard Gorbunov, Alexander Rogozin, Vladislav Matyukhin and me, became the winner of a grant for young research groups.

Nov 30, 2021

Mobirise

New paper out

"Random-reshuffled SARAH does not need a full gradient computations" - joint work with Martin Takac.

Nov 26, 2021

Mobirise

NeurIPS: 4 accepted papers

We have one paper at the main conference. Also we have submitted 3 papers to OPT 2021: Optimization for Machine Learning and New Frontiers in Federated Learning: Privacy, Fairness, Robustness, Personalization and Data Ownership workshops. All were accepted! These papers are

1) Distributed Saddle-Point Problems Under Similarity (with Gesualdo Scutari, Alexander Rogozin and Alexander Gasnikov) - main conference (poster) - arxiv

2) Decentralized Personalized Federated Learning: Lower Bounds and Optimal Algorithm for All Personalization Modes (with Abdurakhmon Sadiev, Ekaterina Borodich, Darina Dvinskikh, Martin Takac and Alexander Gasnikov) - OPT ML workshop (spotlight) - arxiv

3) Random-reshuffled SARAH does not need a full gradient computations (with Martin Takac) - OPT ML workshop (poster)

4) Decentralized Personalized Federated Min-Max Problems (with Ekaterina Borodich, Abdurakhmon Sadiev, Vadim Sushko, Nikolay Savelyev, Martin Takac and Alexander Gasnikov) - NF in FL workshop - arxiv

Oct 22, 2021

Mobirise

New paper out

"Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees" - joint work with Peter Richtárik, Michael Diskin, Max Ryabinin and Alexander Gasnikov.

Oct 7, 2021

Mobirise

I am in MBZUAI till December

My internship as Research Assistant at Martin Takac's group has started today! It is a great pleasure for me to be a part of Martin's team and MBZUAI!

Oct 3, 2021

Mobirise

Paper accepted to NeurIPS

Our joint work with Gesualdo Scutari, Alexander Rogozin and Alexander Gasnikov got accepted and will be presented at NeurIPS in December. Now you can read it on arxiv.

Sep 29, 2021

Mobirise

Teacher on the Probability Theory course

In the new semester I teach the Probability Theory course in MIPT as a seminar teacher.

Sep 1, 2021

Mobirise

New paper out

"Distributed Saddle-Point Problems Under Similarity" - joint work with Gesualdo Scutari, Alexander Rogozin and Alexander Gasnikov.

Jul 22, 2021

Mobirise

New paper out

"Decentralized and Personalized Federated Learning" - Abdurakhmon Sadiev, Darina Dvinskikh and Alexander Gasnikov.

This is a draft version! Work in progress!

Jul 15, 2021

Mobirise

New paper out

"Optimal Decentralized Algorithms for Saddle Point Problems over Time-Varying Networks" - joint work with Alexander Rogozin, Dmitry Kovalev and Alexander Gasnikov.

Jul 13, 2021

Mobirise

New paper out

"One-Point Gradient-Free Methods for Composite Optimization with Applications to Distributed Optimization" - joint work with Ivan Stepanov, Artyom Voronov and Alexander Gasnikov.

This is my students' semester project! I am very glad they did it! That's not all! There will be more projects from my students!

This is a draft version! Work in progress!

Jul 13, 2021

Mobirise

Join Yandex Research team

It is my pleasure to join Yandex Research as a research intern!

Jul 12, 2021

Mobirise

Participation in Conference dedicated to the anniversaries of Yurii Nesterov and Vladimir Protasov

I am taking part in the conference "Optimization without borders" in Sochi. The conference is dedicated to the anniversaries of Yurii Nesetrov and Vladimir Protasov

Jul 11, 2021

Mobirise

Participation in all-Russian Optimization Seminar

I gave a talk about distributed optimization at the all-Russian Optimization Seminar.

Jun 30, 2021

Mobirise

New paper out

"Decentralized Local Stochastic Extra-Gradient for Variational Inequalities" - joint work with Pavel Dvurechensky, Anastasia Koloskova, Valentin Samokhin, Sebastian U Stich, Alexander Gasnikov.

Jun 15, 2021

Mobirise

New paper out

"Decentralized Personalized Federated Min-Max Problems" - joint work with Vadim Sushko, Abdurakhmon Sadiev, Alexander Gasnikov.

Jun 14, 2021

Mobirise

Participation in Control, Information and Optimization Summer School

During the school I will give a 1.5 hour lecture on saddle point problems and variational inequalities.

Jun 11, 2021

Mobirise

Participation in Moscow Conference on Combinatorics and Applications

I gave a 30 minute talk about distributed saddle point problems.

Jun 2, 2021

Mobirise

Poster on Communication Efficient Distributed Optimization Workshop

I was pleased to present my poster, as well as listen to speakers and discuss other posters

Apr 9, 2021

Mobirise

Junior Researcher at the Laboratory of Advanced Combinatorics and
Network Applications

I'm glad to be part of the laboratory team (head: Andrei Raigorodskii)

Mar 1, 2021

Mobirise

New paper out

"One-Point Gradient-Free Methods for Smooth and Non-Smooth Saddle-Point Problems" - joint work with Vasilii Novitskii, Alexander Gasnikov.

Mar 1, 2021

Mobirise

New paper out

"Solving smooth min-min and min-max problems by mixed oracle algorithms" - joint work with Egor Gladin, Abdurakhmon Sadiev, Alexander Gasnikov, Pavel Dvurechensky, Mohammad Alkousa.

Mar 1, 2020

Mobirise

I was awarded a scholarship in the field of numerical optimization methods

The scholarship was established by Professor Andrei Raigorodsky.

Feb 27, 2021

Mobirise

New paper out

"Distributed Saddle-Point Problems: Lower Bounds, Optimal Algorithms and Federated GANs" - joint work with Valentin Samokhin and Alexander Gasnikov. 

Feb 16, 2021

Mobirise

New paper out

"Decentralized Distributed Optimization for Saddle Point Problems" - joint work with Alexander Rogozin, Pavel Dvurechensky, Darina Dvinskikh, Dmitry Kovalev and Alexander Gasnikov.

Feb 15, 2021

Mobirise

Research assistant at the International Laboratory of Stochastic Algorithms and High-Dimensional Inference

I'm glad to be part of the laboratory team (heads: Eric Moulines, Alexey Naumov)

Feb 1, 2021

Mobirise

Teacher on the Stochastic Processes course

In the new semester I will teach the Stochastic Processes course at MIPT as a seminar teacher (lecturer: Maksim Shirobokov).

Feb 1, 2021

Mobirise

New paper out

"Recent theoretical advances in decentralized distributed convex optimization" - joint work with Eduard Gorbunov, Alexander Rogozin, Darina Dvinskikh and Alexander Gasnikov.

Nov 26, 2020

Mobirise

New paper out

"Local SGD for Saddle-Point Problems" - joint work with Valentin Samokhin and Alexander Gasnikov. Work in progress!

Oct 25, 2020

Mobirise

New paper out

"Zeroth-Order Algorithms for Smooth Saddle-Point Problems" - joint work with Abdurakhmon Sadiev, Pavel Dvurechensky and Alexander Gasnikov.

Sep 21, 2020

Mobirise

New paper out

"Linearly Convergent Gradient-Free Methods for Minimization of Symmetric Parabolic Approximation" - joint work with Aleksandra Bazarova and Alexander Gasnikov.

Sep 10, 2020

Mobirise

Teacher on the Probability Theory and Discrete Analysis courses

In the new semester I begin to teach the Probability Theory and Discrete Analysis courses in MIPT as a seminar teacher.

Sep 1, 2020

Mobirise

Visit to Sirius University

During the month I will give several lectures on optimization and will also take part in several projects.

Aug 2, 2020

Mobirise

Our paper was presented at MOTOR 2020

My joint work "Gradient-Free Methods for Saddle-Point Problem" with Abdurakhmon Sadiev and Alexander Gasnikov was presented at the conference and will be published in Communications in Computer and Information Science (CCIS) series.

Jul 15, 2020

Mobirise

Our paper was presented at IFAC 2020

My joint work "Derivative-Free Method For Decentralized Distributed Non-Smooth Optimization" with Eduard Gorbunov and Alexander Gasnikov was presented at the conference and will be published in IFAC-PapersOnLine.

Jul 12, 2020

Mobirise

New paper out

"Gradient-Free Methods for Saddle-Point Problem" - joint work with Abdurakhmon Sadiev and Alexander Gasnikov.

May 12, 2020

Mobirise

New paper out

"On Biased Compression for Distributed Learning" - joint work with Samuel Horváth, Peter Richtárik and Mher Safaryan.
The work was done while I was on an internship at KAUST in the team of professor Peter Richtárik. Thank you Peter for inviting me!

Feb 27, 2020

Mobirise

Advisor on the Machine Learning course

In the new semester I will be a student advisor on the Machine Learning course at Dorodnicyn Computing Centre of RAS.

Feb 13, 2020

Mobirise

Teacher on the Stochastic Processes course

In the new semester I will teach the Stochastic Processes course at MIPT as a seminar teacher (lecturer: Alexander Gasnikov).

Feb 7, 2020

© 2020-2022 Aleksandr Beznosikov