.png){kind=icon}
返回
Robustness and generalization
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-011-5268-1.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We derive generalization bounds for learning algorithms based on their robustness: the property that if a testing sample is similar to a training sample, then the testing error is close to the training error. This provides a novel approach, different from complexity or stability arguments, to study generalization of learning algorithms. One advantage of the robustness approach, compared to previous methods, is the geometric intuition it conveys. Consequently, robustness-based analysis is easy to extend to learning in non-standard setups such as Markovian samples or quantile loss. We further show that a weak notion of robustness is both sufficient and necessary for generalizability, which implies that robustness is a fundamental property that is required for learning algorithms to work.
Keyword:
Generalization
Robust
Non-IID sample
Quantile loss
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
A GEOGRAPHIC WEIGHTED REGRESSION FOR RURAL HIGHWAYS CRASHES MODELLING USING THE GAUSSIAN AND TRICUBE KERNELS: A CASE STUDY OF USA RURAL HIGHWAYS.png)
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesOAAI
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesIF0
OAAI分享收藏
查看更多内容