Implicit Kernel Learning

Abstract

Kernels are powerful and versatile tools in machine learning and statistics. Although the notion of universal kernels and characteristic kernels has been studied, kernel selection still greatly influences the empirical performance. While learning the kernel in a data driven way has been investigated, in this paper we explore learning the spectral distribution of kernel via implicit generative models parametrized by deep neural networks. We called our method Implicit Kernel Learning (IKL). The proposed framework is simple to train and inference is performed via sampling random Fourier features. We investigate two applications of the proposed IKL as examples, including generative adversarial networks with MMD (MMD GAN) and standard supervised learning. Empirically, MMD GAN with IKL outperforms vanilla predefined kernels on both image and text generation benchmarks; using IKL with Random Kitchen Sinks also leads to substantial improvement over existing state-of-the-art kernel learning algorithms on popular supervised learning benchmarks. Theory and conditions for using IKL in both applications are also studied as well as connections to previous state-of-the-art methods.

In the Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019)

Cited by in corpus (12)

• Learning with Density Matrices and Random Features
• Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond
• End-to-end Kernel Learning via Generative Random Fourier Features
• Generative Ratio Matching Networks
• Kernel Stein Generative Modeling
• Kernel-Based Models for Influence Maximization on Graphs based on Gaussian Process Variance Minimization
• Learning Manifold Implicitly via Explicit Heat-Kernel Learning
• On Learning the Transformer Kernel
• A Mean-Field Theory for Kernel Alignment with Random Features in Generative and Discriminative Models
• KernelNet: A Data-Dependent Kernel Parameterization for Deep Generative Modeling
• Learning Data-adaptive Nonparametric Kernels
• Generalization Properties of hyper-RKHS and its Applications