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：

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Efficiency - Number theory - Parameterization

引用

共 50 条

[21] NON-ERGODIC LINEAR CONVERGENCE PROPERTY OF THE DELAYED GRADIENT DESCENT UNDER THE STRONGLY CONVEXITY AND THE POLYAK-LOJASIEWICZ CONDITION
Choi, Hyung Jun
Choi, Woocheol
Seok, Jinmyoung
arXiv, 2023,
[22] On the Complexity of Finite-Sum Smooth Optimization under the Polyak–Lojasiewicz Condition
Bai, Yunyan
Liu, Yuxing
Luo, Luo
arXiv,
[23] Non-ergodic linear convergence property of the delayed gradient descent under the strongly convexity and the Polyak-Lojasiewicz condition
Choi, Hyung Jun
Choi, Woocheol
Seok, Jinmyoung
ANALYSIS AND APPLICATIONS, 2024, 22 (06) : 1023 - 1051
[24] Sparse optimization on measures with over-parameterized gradient descent
Lénaïc Chizat
Mathematical Programming, 2022, 194 : 487 - 532
[25] Sparse optimization on measures with over-parameterized gradient descent
Chizat, Lenaic
MATHEMATICAL PROGRAMMING, 2022, 194 (1-2) : 487 - 532
[26] On over-parameterized model based TV-denoising
Nir, Tal
Bruckstem, Alfred M.
ISSCS 2007: INTERNATIONAL SYMPOSIUM ON SIGNALS, CIRCUITS AND SYSTEMS, VOLS 1 AND 2, 2007, : 279 - +
[27] Orthogonal Over-Parameterized Training
Liu, Weiyang
Lin, Rongmei
Liu, Zhen
Rehg, James M.
Paull, Liam
Xiong, Li
Song, Le
Weller, Adrian
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 7247 - 7256
[28] POLYAK-LOJASIEWICZ INEQUALITY ON THE SPACE OF MEASURES AND CONVERGENCE OF MEAN-FIELD BIRTH-DEATH PROCESSES
Liu, Linshan
Majka, Mateusz B.
Szpruch, Lukasz
arXiv, 2022,
[29] Understanding Implicit Regularization in Over-Parameterized Single Index Model
Fan, Jianqing
Yang, Zhuoran
Yu, Mengxin
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2023, 118 (544) : 2315 - 2328
[30] Smooth over-parameterized solvers for non-smooth structured optimization
Clarice Poon
Gabriel Peyré
Mathematical Programming, 2023, 201 : 897 - 952

← 1 2 3 4 5 →