Xun Qian

9 papers · 2019–2023 · 4 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (4) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (12) 🐝 Cross-Pollinator (11) 🔥 Unstoppable (5)

Conferences

ICML (5) AISTATS (2) JMLR (1) NIPS (1)

Top co-authors

Peter Richtarik (9) Rustem Islamov (3) Mher Safaryan (2) Tong Zhang (2) Zheng Qu (2) Zhize Li (1) Dmitry Kovalev (1) Hanze Dong (1) Nicolas Loizou (1) Robert Mansel Gower (1)

Keywords

stochastic gradient descent (4) distributed optimization (3) federated learning (3) communication compression (3) variance reduction (2) communication efficiency (2) error compensation (2) newton method (2) communication efficient (2) second-order method (2) arbitrary sampling (2) convergence analysis (1) distributed training (1) second-order optimization (1) finite-sum optimization (1) stochastic optimization (1) gradient descent (1) importance sampling (1) gradient compression (1) iteration complexity (1)

Papers

Catalyst Acceleration of Error Compensated Methods Leads to Better Communication Complexity AISTATS 2023

FedNL: Making Newton-Type Methods Applicable to Federated Learning ICML 2022

Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning AISTATS 2022

Error Compensated Distributed SGD Can Be Accelerated NIPS 2021

Distributed Second Order Methods with Fast Rates and Compressed Communication ICML 2021

L-SVRG and L-Katyusha with Arbitrary Sampling JMLR 2021

Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization ICML 2020

SAGA with Arbitrary Sampling ICML 2019

SGD: General Analysis and Improved Rates ICML 2019