MLSP-33: Optimization Methods |
Session Type: Poster |
Time: Thursday, 10 June, 15:30 - 16:15 |
Location: Gather.Town |
Virtual Session: View on Virtual Platform |
Session Chair: Konstantinos Slavakis, University at Buffalo |
MLSP-33.1: IMPROVED STEP-SIZE SCHEDULES FOR NOISY GRADIENT METHODS |
Sarit Khirirat; KTH Royal Institute of Technology |
Xiaoyu Wang; KTH Royal Institute of Technology |
Sindri Magnússon; Stockholm University |
Mikael Johansson; KTH Royal Institute of Technology |
MLSP-33.2: RESPIPE: RESILIENT MODEL-DISTRIBUTED DNN TRAINING AT EDGE NETWORKS |
Pengzhen Li; University of Illinois at Chicago |
Erdem Koyuncu; University of Illinois at Chicago |
Hulya Seferoglu; University of Illinois at Chicago |
MLSP-33.3: AN OPTIMAL STOCHASTIC COMPOSITIONAL OPTIMIZATION METHOD WITH APPLICATIONS TO META LEARNING |
Yuejiao Sun; University of California, Los Angeles |
Tianyi Chen; Rensselaer Polytechnic Institute |
Wotao Yin; University of California, Los Angeles |
MLSP-33.4: DECENTRALIZED OPTIMIZATION ON TIME-VARYING DIRECTED GRAPHS UNDER COMMUNICATION CONSTRAINTS |
Yiyue Chen; University of Texas at Austin |
Abolfazl Hashemi; University of Texas at Austin |
Haris Vikalo; University of Texas at Austin |
MLSP-33.5: DECENTRALIZED DEEP LEARNING USING MOMENTUM-ACCELERATED CONSENSUS |
Aditya Balu; Iowa State University |
Zhanhong Jiang; Johnson Controls |
Sin Yong Tan; Iowa State University |
Chinmay Hedge; New York University |
Young M Lee; Johnson Controls |
Soumik Sarkar; Iowa State University |
MLSP-33.6: DEMYSTIFYING MODEL AVERAGING FOR COMMUNICATION-EFFICIENT FEDERATED MATRIX FACTORIZATION |
Shuai Wang; The Chinese University of Hong Kong, Shenzhen |
Richard Cornelius Suwandi; The Chinese University of Hong Kong, Shenzhen |
Tsung-Hui Chang; The Chinese University of Hong Kong, Shenzhen |