2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2021 Open Preview.

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