A Class of Random-Kernel Network Models
We introduce random-kernel networks, a multilayer extension of random feature models where depth is created by deterministic kernel composition and randomness enters only in the outermost layer. We prove that deeper constructions can approximate certain functions with fewer Monte Carlo samples than any shallow counterpart, establishing a depth separation theorem in sample complexity.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
The Random Forest Kernel and other kernels for big data from random partitions
We present Random Partition Kernels, a new class of kernels derived by demonstrating a natural connection between random partitions of objects and kernels between those objects. We show how the construction can be used t…
Gaussian ProcessesS-Rocket: Selective Random Convolution Kernels for Time Series Classification
Random convolution kernel transform (Rocket) is a fast, efficient, and novel approach for time series feature extraction using a large number of independent randomly initialized 1-D convolution kernels of different confi…
Combinatorial OptimizationregressionTime SeriesTime Series Analysis+1Weisfeiler and Leman Go Walking: Random Walk Kernels Revisited
Random walk kernels have been introduced in seminal work on graph learning and were later largely superseded by kernels based on the Weisfeiler-Leman test for graph isomorphism. We give a unified view on both classes of …
Graph LearningData Dependent Kernel Approximation using Pseudo Random Fourier Features
Kernel methods are powerful and flexible approach to solve many problems in machine learning. Due to the pairwise evaluations in kernel methods, the complexity of kernel computation grows as the data size increases; thus…
Fast Graph Kernel with Optical Random Features
The graphlet kernel is a classical method in graph classification. It however suffers from a high computation cost due to the isomorphism test it includes. As a generic proxy, and in general at the cost of losing some in…
Graph Classification