SPTM-P19.8
DECENTRALIZED LEARNING WITH DYNAMICALLY REFINED EDGE WEIGHTS: A DATA-DEPENDENT FRAMEWORK
Rongxing Du, Hoi To Wai, The Chinese University of Hong Kong, Hong Kong
Session:
SPTM-P19: Distributed Optimization I Poster
Track:
Signal Processing Theory and Methods [TM]
Location:
Poster Area 2
Presentation Time:
Tue, 5 May, 14:00 - 16:00
Presentation
Discussion
Resources
No resources available.
Session SPTM-P19
SPTM-P19.1: UNDERSTANDING GENERALIZATION IN DECENTRALIZED LEARNING: A TIME-UNIFORM AND TOPOLOGY-AWARE ANALYSIS
Haoxiang Ye, Sun Yat-Sen University, China; Tao Sun, National University of Defense Technology, China; Qing Ling, Sun Yat-Sen University, China
SPTM-P19.2: FROM POWERSGD TO POWERSGD+: LOW-RANK GRADIENT COMPRESSION FOR DISTRIBUTED OPTIMIZATION WITH CONVERGENCE GUARANTEES
Shengping Xie, Chuyan Chen, Kun Yuan, Peking University, China
SPTM-P19.3: Stability and Generalization of Adversarial Diffusion Training
Hesam Hosseini, Ying Cao, Ali H. Sayed, École Polytechnique Fédérale de Lausanne, Switzerland
SPTM-P19.4: DIFFERENTIALLY PRIVATE DECENTRALIZED CONSTRAINED LEARNING WITH DUAL AVERAGING
Robin Francis, Sundeep Prabhakar Chepuri, Indian Institute of Science, India
SPTM-P19.5: Diffusion Stochastic Learning over Multi-Team Network Games
Wen Perng, National Taiwan University, Taiwan; Vladyslav Shashkov, Haoyuan Cai, Ali Sayed, EPFL, Switzerland
SPTM-P19.6: EFFICIENT SYNTHETIC DATA SELECTION VIA PONTRYAGIN’S MAXIMUM PRINCIPLE
Xinyuan Zhao, Tsinghua University, China; Hanlin Gu, WeBank, China; Guibao Song, Gongxi Zhu, Yuxing Han, Tsinghua University, China
SPTM-P19.7: PROXICBO: A CONSENSUS-BASED METHOD FOR COMPOSITE OPTIMIZATION
Haoyu Zhang, University of California San Diego, United States of America; Yanting Ma, Mitsubishi Electric Research Laboratories (MERL), United States of America; Ruangrawee Kitichotkul, Boston University, United States of America; Joshua Rapp, Petros Boufounos, Mitsubishi Electric Research Laboratories (MERL), United States of America
SPTM-P19.8: DECENTRALIZED LEARNING WITH DYNAMICALLY REFINED EDGE WEIGHTS: A DATA-DEPENDENT FRAMEWORK
Rongxing Du, Hoi To Wai, The Chinese University of Hong Kong, Hong Kong
SPTM-P19.9: GRAPH-AWARE LEARNING RATES FOR DECENTRALIZED OPTIMIZATION
Aaron Fainman, Stefan Vlaski, Imperial College London, United Kingdom of Great Britain and Northern Ireland
SPTM-P19.10: FAIRMOO: ACHIEVING FAIRNESS IN DISTRIBUTED LEARNING VIA CONSTRAINED MULTI-OBJECTIVE OPTIMIZATION
Huigan Zheng, Sun Yat-Sen University, China; Jiaojiao Zhang, Great Bay University, China; Yongxiang Liu, Pengcheng Laboratory, China; Qing Ling, Sun Yat-Sen University, China
Contacts