Characterizing Implicit Bias in Terms of Optimization Geometry

登录免费注册

资源分类

论文
算法
数据集
经验分享
技术动态
行业动态

论文
学习
研究领域

算法
学习
研究领域

数据集
自动驾驶
图片

经验分享
学习
研究领域

技术动态
计算机视觉
自然语言处理

行业动态
教育
语音识别

》资源》论文》Characterizing Implicit Bias in Terms of Optimization Geometry

Characterizing Implicit Bias in Terms of Optimization Geometry

2020-03-20 |

119 |

120 |

Characterizing Implicit Bias in Terms of Optimization Geometry
论文

Abstract

We study the implicit bias of generic optimization methods—mirror descent, natural gradient descent, and steepest descent with respect to different potentials and norms—when optimizing underdetermined linear regression or separable linear classification problems. We explore the question of whether the specific global minimum (among the many possible global minima) reached by an algorithm can be characterized in terms of the potential or norm of the optimization geometry, and independently of hyperparameter choices such as step–size and momentum.

上一篇：Improved nearest neighbor search using auxiliary information and priority functions

下一篇：Black-box Adversarial Attacks with Limited Queries and Information

用户评价