Rustem Islamov

Master student

IP Paris

Bio

I am a second year Master student at Institut Polytechnique de Paris. Prior to that, I obtained my Bachelor diploma from Moscow Institute of Physics and Technology. I am interested in Optimization and its applications to Machine Learning. Currently I am working under supervision of Olivier Fercoq. Besides, I am also supervised by Peter Richtárik.

On top of that, I am a big fan of football and judo.

Computer skills

Programming languages: Python, LaTeX, C/C++

Interests

Optimization
Machine Learning
Federated learning

Education

Master of Science in Applied Mathematics and Statistics

IP Paris, Department of Applied Mathematics

Sept. 2021 – Present GPA 18.18/20 Palaiseau, France

Supervisor: Olivier Fercoq

Master of Science in Applied Mathematics and Physics

MIPT, Phystech School of Applied Mathematics and Informatics

Sept. 2021 – Present GPA 5/5 (9.2/10) Dologprudny, Russia

Supervisor: Vadim Strijov

Bachelor of Science in Applied Mathematics and Physics

MIPT, Phystech School of Applied Mathematics and Informatics

Sept. 2017 – Jul. 2021 GPA 4.95/5 (9.27/10)Dolgoprudny, Russia

Thesis: Distributed Second Order Methods with Fast Rates and Compressed Communication

Supervisor: Peter Richtárik

Recent Posts

Recent news of the fall

I am happy to announce that our recent paper was accepted to NeurIPS workshop HOO 2022: Order up! The Benefits of Higher-Order Optimization in Machine Learning. Besides, new paper on adaptive compression for Federated Learning has been just published on arXiv.

Start of new academic year

I am starting my second year of Master at IP Paris. This year my Master program is based on Data Science program of Ecole Polytechnique.

New paper out

In our new paper we prove that a class of so called Three Point Compressors can be applied on Newton method. This result opens up a wide variety of communication strategies, such as a combination of contractive compression and lazy aggregation, available to our disposal to compress prohibitively costly curvature information.

One paper was accepted to ICML 2022

I am very proud to announce that our FedNL paper was accepted to 39th International Conference on Machine Learning (ICML 2022).

Internship at MLO Lab, EPFL

Currenly I am in Lausanne. Here I have started my internship at Machine Learning and Optimization Lab, EPFL run by Prof. Martin Jaggi. I will work under the supervision of postdoctoral fellow Hadrien Hendrikx and Prof. Martin Jaggi.

See all posts