A Spectral Analysis of Dot-product Kernels
arXiv:2002.12640
Abstract
We present eigenvalue decay estimates of integral operators associated with compositional dot-product kernels. The estimates improve on previous ones established for power series kernels on spheres. This allows us to obtain the volumes of balls in the corresponding reproducing kernel Hilbert spaces. We discuss the consequences on statistical estimation with compositional dot product kernels and highlight interesting trade-offs between the approximation error and the statistical error depending on the number of compositions and the smoothness of the kernels.
References in corpus (9)
- Neural Tangent Kernel: Convergence and Generalization in Neural Networks
- A Mean Field View of the Landscape of Two-Layers Neural Networks
- Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity
- Convolutional Kernel Networks
- A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks
- Sobolev Norm Learning Rates for Regularized Least-Squares Algorithm
- Learning with Group Invariant Features: A Kernel Perspective
- Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance
- Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS