Avatar

Egor Shulgin

PhD student

KAUST

Biography

I am a PhD student working on optimization for machine learning and federated learning at King Abdullah University of Science and Technology (KAUST), advised by Peter Richtárik.

Apart from research, I am also passionate about hiking/backpacking, alpine skiing, and rationality.

Interests

  • Optimization for Machine Learning
  • Federated Learning

Education

  • BSc in Applied Mathematics, Computer Science and Physics, 2019

    Moscow Institute of Physics and Technology

Recent Posts

Paper accepted to ICML 2021

ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks was accepted to ICML 2021.
May 11, 2021 1 min read

KAUST Conference on Artificial Intelligence

I prepared a 5-minute presentation of our recent work on ADOM for KAUST Conference on Artificial Intelligence.
May 11, 2021 1 min read

Attendance of NSF-TRIPODS Workshop

I presented (virtually) a poster about our recent work on ADOM at Communication Efficient Distributed Optimization Workshop.
Apr 11, 2021 1 min read

New Paper out

ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks
May 11, 2021 1 min read

Paper Accepted to Information and Inference: A Journal of the IMA

Title: Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal …
Jan 24, 2021 1 min read
See all posts

Recent Publications

Quickly discover relevant content by filtering publications.

Shifted Compression Framework: Generalizations and Improvements

We develop a unified framework for studying distributed optimization methods with compression.
Poster Slides Video arXiv OpenReview

ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks

We propose ADOM – an accelerated method for smooth and strongly convex decentralized optimization over time-varying networks.
Poster arXiv 5-min video

Revisiting Stochastic Extragradient

We fix a fundamental issue in the stochastic extragradient method by providing a new sampling strategy.
PDF Video arXiv AISTATS 2020 Proceedings NeurIPS 2019 Workshop

Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor

In order to mitigate the high communication cost in distributed and federated learning, various vector compression schemes, such as …
PDF arXiv

Adaptive Catalyst for Smooth Convex Optimization

We present a generic framework that allows accelerating almost arbitrary non-accelerated algorithms for smooth convex optimization …
PDF arXiv
See all publications

Contact