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
来源：
Journal of Machine Learning Research | 2018年 / 19卷
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
  • [11] Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data
    Kou, Yiwen
    Chen, Zixiang
    Gu, Quanquan
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [12] Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network
    Lyu, Bochen
    Zhu, Zhanxing
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [13] Gradient descent for deep matrix factorization: Dynamics and implicit bias towards low rank
    Chou, Hung-Hsu
    Gieshoff, Carsten
    Maly, Johannes
    Rauhut, Holger
    APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2024, 68
  • [14] Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate
    Nacson, Mor Shpigel
    Srebro, Nathan
    Soudry, Daniel
    22ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 89, 2019, 89
  • [15] A coordinate gradient descent method for nonsmooth separable minimization
    Paul Tseng
    Sangwoon Yun
    Mathematical Programming, 2009, 117 : 387 - 423
  • [16] A coordinate gradient descent method for nonsmooth separable minimization
    Tseng, Paul
    Yun, Sangwoon
    MATHEMATICAL PROGRAMMING, 2009, 117 (1-2) : 387 - 423
  • [17] Bias of Homotopic Gradient Descent for the Hinge Loss
    Denali Molitor
    Deanna Needell
    Rachel Ward
    Applied Mathematics & Optimization, 2021, 84 : 621 - 647
  • [18] Bias of Homotopic Gradient Descent for the Hinge Loss
    Molitor, Denali
    Needell, Deanna
    Ward, Rachel
    APPLIED MATHEMATICS AND OPTIMIZATION, 2021, 84 (01): : 621 - 647
  • [19] An implicit gradient-descent procedure for minimax problems
    Essid, Montacer
    Tabak, Esteban G.
    Trigila, Giulio
    MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2023, 97 (01) : 57 - 89
  • [20] 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
12345