.png){kind=icon}
返回
Error scaling laws for kernel classification under source and capacity conditions
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/acf041.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this manuscript we consider the problem of kernel classification. While worst-case bounds on the decay rate of the prediction error with the number of samples are known for some classifiers, they often fail to accurately describe the learning curves of real data sets. In this work, we consider the important class of data sets satisfying the standard source and capacity conditions, comprising a number of real data sets as we show numerically. Under the Gaussian design, we derive the decay rates for the misclassification (prediction) error as a function of the source and capacity coefficients. We do so for two standard kernel classification settings, namely margin-maximizing support vector machines and ridge classification, and contrast the two methods. We find that our rates tightly describe the learning curves for this class of data sets, and are also observed on real data. Our results can also be seen as an explicit prediction of the exponents of a scaling law for kernel classification that is accurate on some real datasets.
Keyword:
kernels
statistical physics
generalization error rates
期刊
M
IF:
4.6
论文数:
1.1K
被引数:
3.4K
机构
引用论文
分享收藏HIGH-DIMENSIONAL ASYMPTOTICS OF PREDICTION: RIDGE REGRESSION AND CLASSIFICATION.png)
ANNALS OF STATISTICS
OAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏分享收藏Separation of scales and a thermodynamic description of feature learning in some CNNsNATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networksNATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏
查看更多内容