Egor Shulgin

6 papers · 2019–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14) 🧬 Topic Evolution

Venues

ICML (3) AISTATS (1) ICLR (1) UAI (1)

Top co-authors

Peter Richtarik (6) Dmitry Kovalev (2) Alexander V Rogozin (1) Konstantin Mishchenko (1) Alibek Sailanbayev (1) Alexander Gasnikov (1) Grigory Malinovsky (1) Yura Malitsky (1) Yury Demidovich (1) Nicolas Loizou (1)

Research topics

Machine Learning (6) Optimization & Theory (5) Mathematics & Optimization (3) Optimization (3) Application Areas (2) Deep Learning (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1)

Keywords

stochastic gradient descent (3) variance reduction (2) variational inequality (1) convergence analysis (1) distributed learning (1) decentralized optimization (1) model parallelism (1) quadratic models (1) distributed training (1) communication efficiency (1) convex-concave saddle-point (1) saddle-point problems (1) convergence rate (1) gradient compression (1) communication compression (1) generative adversarial network (1) sparse training (1) nesterov acceleration (1) model sparsification (1) bilinear game (1)

Papers

MAST: model-agnostic sparsified training ICLR 2025 Towards a Better Theoretical Understanding of Independent Subnetwork Training ICML 2024 Shifted compression framework: generalizations and improvements UAI 2022 ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks ICML 2021 Revisiting Stochastic Extragradient AISTATS 2020 SGD: General Analysis and Improved Rates ICML 2019