.png){kind=icon}
返回
Pairwise Learning With Gaussian Empirical Gain Function
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3507539.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This article investigate the performance of Gaussian Empirical Gain Maximization (EGM) in a regression setting and conduct a detailed theoretical analysis, particularly in the presence of heavy-tailed noise, where this article establish improved convergence rates. To achieve this, this article introduce a new moment condition, from which this article derive several enhanced theoretical results for the Gaussian model. First, propose a new comparison theorem, proving that this theorem plays a crucial role in improving the estimation of approximation errors and variance. This theorem not only characterizes the regression properties of Gaussian EGM but also plays a key role in enhancing the convergence rate. Secondly, This article derive improved error bounds for the Gaussian model, providing theoretical support for the application of Gaussian EGM under different noise conditions. broadens our theoretical understanding of Gaussian EGM.
Keyword:
Robustness
Noise
Convergence
Reactive power
Random variables
Entropy
Machine learning
Estimation
Predictive models
Kernel
Empirical gain maximization (EGM)
convergence rates
gauss gain function
heavy-tailed noise
weak moment condition
concentration inequality
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Tuberculosis control in resource-poor countries: alternative approaches in the era of HIV.png)
The Lancet
The LancetIF0
PREAI
分享收藏
Possible risk factors in the development of eating disorders in overweight pre-adolescent girls
PREAI
分享收藏Lateral Resistance of Unreinforced Masonry Walls Strengthened With Engineered Cementitious Composite
PREAI
分享收藏
查看更多内容