OVER-PARAMETERIZED MODEL OPTIMIZATION WITH POLYAK-LOJASIEWICZ CONDITION

被引：0
|
作者：
Chen, Yixuan [1 ]
Shi, Yubin [1 ]
Dong, Mingzhi [1 ]
Yang, Xiaochen [2 ]
Li, Dongsheng [3 ]
Wang, Yujiang [4 ]
Dick, Robert P. [5 ]
Lv, Qin [6 ]
Zhao, Yingying [1 ]
Yang, Fan [7 ]
Gu, Ning [1 ]
Shang, Li [1 ]
机构：
[1] China and Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai, China
[2] School of Mathematics Statistics, The University of Glasgow, Glasgow, United Kingdom
[3] Microsoft Research Asia, Shanghai, China
[4] Department of Engineering Science, University of Oxford, Oxford, United Kingdom
[5] Department of Electrical Engineering and Computer Science, University of Michigan, Michigan, United States
[6] Department of Computer Science, University of Colorado Boulder, Boulder,CO, United States
[7] School of Microelectronics, Fudan University, Shanghai, China
来源：
11th International Conference on Learning Representations, ICLR 2023 | 2023年
关键词：
Compilation and indexing terms; Copyright 2025 Elsevier Inc;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Efficiency - Number theory - Parameterization
引用
收藏
相关论文
共 50 条
  • [31] Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks
    Soltanolkotabi, Mahdi
    Javanmard, Adel
    Lee, Jason D.
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2019, 65 (02) : 742 - 769
  • [32] Smooth over-parameterized solvers for non-smooth structured optimization
    Poon, Clarice
    Peyre, Gabriel
    MATHEMATICAL PROGRAMMING, 2023, 201 (1-2) : 897 - 952
  • [33] Polyak-Lojasiewicz inequality on the space of measures and convergence of mean-field birth-death processes
    Liu, Linshan
    Majka, Mateusz B.
    Szpruch, Lukasz
    APPLIED MATHEMATICS AND OPTIMIZATION, 2023, 87 (03):
  • [34] Over-parameterized variational optical flow
    Nir, Tal
    Bruckstein, Alfred M.
    Kimmel, Ron
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2008, 76 (02) : 205 - 216
  • [35] Over-Parameterized Variational Optical Flow
    Tal Nir
    Alfred M. Bruckstein
    Ron Kimmel
    International Journal of Computer Vision, 2008, 76 : 205 - 216
  • [36] Convergence Analysis for Over-Parameterized Deep Learning
    Jiao, Yuling
    Lu, Xiliang
    Wu, Peiying
    Yang, Jerry Zhijian
    COMMUNICATIONS IN COMPUTATIONAL PHYSICS, 2024, 36 (01) : 71 - 103
  • [37] Decentralized Federated Learning for Over-Parameterized Models
    Qin, Tiancheng
    Etesami, S. Rasoul
    Uribe, Cesar A.
    2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC), 2022, : 5200 - 5205
  • [38] Investigating over-parameterized randomized graph networks
    Donghi, Giovanni
    Pasa, Luca
    Oneto, Luca
    Gallicchio, Claudio
    Micheli, Alessio
    Anguita, Davide
    Sperduti, Alessandro
    Navarin, Nicolo
    NEUROCOMPUTING, 2024, 606
  • [39] Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
    Liu, Chaoyue
    Zhu, Libin
    Belkin, Mikhail
    APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2022, 59 : 85 - 116
  • [40] OVER-PARAMETERIZED NETWORK SOLVES PHASE RETRIEVAL EFFECTIVELY
    Li, Ji
    Wang, Chao
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 4133 - 4137
12345