The implicit bias of gradient descent on separable data

被引:0
|
作者
Soudry, Daniel [1 ]
Hoffer, Elad [1 ]
Nacson, Mor Shpigel [1 ]
Gunasekar, Suriya [2 ]
Srebro, Nathan [2 ]
机构
[1] Department of Electrical Engineering, Technion Haifa, 320003, Israel
[2] Toyota Technological Institute at Chicago, Chicago,IL,60637, United States
关键词
Compendex;
D O I
暂无
中图分类号
学科分类号
摘要
Gradient methods - Support vector machines - Regression analysis
引用
收藏
相关论文
共 50 条
  • [21] The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models
    Wang, Li
    Fu, Zhiguo
    Zhou, Yingcong
    Yan, Zili
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 8, 2023, : 10149 - 10156
  • [22] An implicit gradient-descent procedure for minimax problems
    Montacer Essid
    Esteban G. Tabak
    Giulio Trigila
    Mathematical Methods of Operations Research, 2023, 97 : 57 - 89
  • [23] Implicit Bias of Gradient Descent for Mean Squared Error Regression with Two-Layer Wide Neural Networks
    Jin, Hui
    Montufar, Guido
    JOURNAL OF MACHINE LEARNING RESEARCH, 2023, 24
  • [24] On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
    Azulay, Shahar
    Moroshko, Edward
    Nacson, Mor Shpigel
    Woodworth, Blake
    Srebro, Nathan
    Globerson, Amir
    Soudry, Daniel
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [25] Efficient gradient descent algorithm with anderson acceleration for separable nonlinear models
    Chen, Guang-Yong
    Lin, Xin
    Xue, Peng
    Gan, Min
    NONLINEAR DYNAMICS, 2025, 113 (10) : 11371 - 11387
  • [26] Learning a Single Neuron with Bias Using Gradient Descent
    Vardi, Gal
    Yehudai, Gilad
    Shamir, Ohad
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [27] Scalable statistical inference for averaged implicit stochastic gradient descent
    Fang, Yixin
    SCANDINAVIAN JOURNAL OF STATISTICS, 2019, 46 (04) : 987 - 1002
  • [28] STOCHASTIC GRADIENT DESCENT FOR SPECTRAL EMBEDDING WITH IMPLICIT ORTHOGONALITY CONSTRAINT
    El Gheche, Mireille
    Chierchia, Giovanni
    Frossard, Pascal
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 3567 - 3571
  • [29] An Accelerated Coordinate Gradient Descent Algorithm for Non-separable Composite Optimization
    Aviad Aberdam
    Amir Beck
    Journal of Optimization Theory and Applications, 2022, 193 : 219 - 246
  • [30] An Accelerated Coordinate Gradient Descent Algorithm for Non-separable Composite Optimization
    Aberdam, Aviad
    Beck, Amir
    JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2022, 193 (1-3) : 219 - 246