Convergence of Iterative Hard Thresholding Variants with Application to Asynchronous Parallel Methods for Sparse Recovery

被引：0
|
作者：
Haddock, Jamie [1 ]
Needell, Deanna [1 ]
Zaeemzadeh, Alireza [2 ]
Rahnavard, Nazanin [2 ]
机构：
[1] Univ Calif Los Angeles, Dept Math, Los Angeles, CA 90024 USA
[2] Univ Cent Florida, Sch Elect Engn & Comp Sci, Orlando, FL 32816 USA
来源：
CONFERENCE RECORD OF THE 2019 FIFTY-THIRD ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS | 2019年
基金：
美国国家科学基金会;
关键词：
D O I：
10.1109/ieeeconf44664.2019.9048787
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Recently several asynchronous parallel algorithms for sparse recovery have been proposed. These methods share an estimation of the support of the signal between nodes, which then use this information in addition to their local estimation of the support to update via an iterative hard thresholding (IHT) method. We analyze a generalized version of the IHT method run on each of the nodes and show that this method performs at least as well as the standard IHT method. We perform numerical simulations that illustrate the potential advantage these methods enjoy over the standard IHT.
引用
收藏
页码：276 / 279
页数：4
相关论文
共 50 条
  • [31] On Local Linear Convergence Rate of Iterative Hard Thresholding for Matrix Completion
    Vu, Trung
    Chunikhina, Evgenia
    Raich, Raviv
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2022, 70 : 5940 - 5953
  • [32] Sparse Recovery on GPUs: Accelerating the Iterative Soft-Thresholding Algorithm
    Shah, Achal
    Majumdar, Angshul
    2014 IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY (ISSPIT), 2014, : 91 - 95
  • [33] A decentralized convergence detection algorithm for asynchronous parallel iterative algorithms
    Bahi, JM
    Contassot-Vivier, S
    Couturier, R
    Vernier, F
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2005, 16 (01) : 4 - 13
  • [34] Iterative hard thresholding methods for regularized convex cone programming
    Lu, Zhaosong
    MATHEMATICAL PROGRAMMING, 2014, 147 (1-2) : 125 - 154
  • [35] BUILDING RECURRENT NETWORKS BY UNFOLDING ITERATIVE THRESHOLDING FOR SEQUENTIAL SPARSE RECOVERY
    Wisdom, Scott
    Powers, Thomas
    Pitton, James
    Atlas, Les
    2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 4346 - 4350
  • [36] On convergence of iterative thresholding algorithms to approximate sparse solution for composite nonconvex optimization
    Hu, Yaohua
    Hu, Xinlin
    Yang, Xiaoqi
    MATHEMATICAL PROGRAMMING, 2024, 211 (1) : 181 - 206
  • [37] Enhanced Iterative Hard Thresholding for the Estimation of Discrete-Valued Sparse Signals
    Sparrer, Susanne
    Fischer, Robert F. H.
    2016 24TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2016, : 71 - 75
  • [38] A Preconditioned Fast Iterative Hard Thresholding Algorithm for Spectrally Sparse Signal Reconstruction
    Bian, Fengmiao
    Cai, Jian-Feng
    Quan, Xueyang
    Wang, Yang
    2024 IEEE 13RD SENSOR ARRAY AND MULTICHANNEL SIGNAL PROCESSING WORKSHOP, SAM 2024, 2024,
  • [39] AN ITERATIVE HARD THRESHOLDING APPROACH TO l0 SPARSE HELLINGER NMF
    O'Hanlon, Ken
    Sandler, Mark B.
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 4737 - 4741
  • [40] Convergence on Thresholding-Based Algorithms for Dictionary-Sparse Recovery
    Hong, Yusu
    Lin, Junhong
    JOURNAL OF FOURIER ANALYSIS AND APPLICATIONS, 2025, 31 (01)
12345