Error Scaling Laws for Kernel Classification under Source and Capacity Conditions

Abstract

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 (SVM) 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.

References in corpus (14)

• Benign Overfitting in Linear Regression
• Fast learning rates for plug-in classifiers
• Fast rates for support vector machines using Gaussian kernels
• Statistical Mechanics of Support Vector Networks
• Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks
• Random design analysis of ridge regression
• Optimal Rates for Spectral Algorithms with Least-Squares Regression over Hilbert Spaces
• Statistical Mechanics of Deep Linear Neural Networks: The Back-Propagating Kernel Renormalization
• Ridge regression and asymptotic minimax estimation over spheres of growing dimension
• Asymptotic learning curves of kernel methods: empirical data v.s. Teacher-Student paradigm
• Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization
• Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration
• On the proliferation of support vectors in high dimensions
• Learning curves for Gaussian process regression with power-law priors and targets