Random Features for Compositional Kernels

2017/03/22 by Amit Daniely, Daniely, Amit, Roy Frostig +5 · 2 citations
Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.1703.07872

openalex publication_date 2017/03/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We describe and analyze a simple random feature scheme (RFS) from prescribed compositional kernels. The compositional kernels we use are inspired by the structure of convolutional neural networks and kernels. The resulting scheme yields sparse and efficiently computable features. Each random feature can be represented as an algebraic expression over a small number of (random) paths in a composition tree. Thus, compositional random features can be stored compactly. The discrete nature of the generation process enables de-duplication of repeated features, further compacting the representation and increasing the diversity of the embeddings. Our approach complements and can be combined with previous random feature schemes.

Citations

• Breaking the Curse of Dimensionality with Convex Neural Networks
• Learning Multiple Layers of Features from Tiny Images

Cited by

• A Correspondence Between Random Neural Networks and Statistical Field\n Theory
• Kernel-based Translations of Convolutional Networks

Related

• All Random Features Representations are Equivalent
• Compact Random Feature Maps
• A Class of Random-Kernel Network Models
• When does compositional structure yield compositional generalization? A kernel theory
• Feature maps for the Laplacian kernel and its generalizations