Rate-Distortion Bounds for Kernel-Based Distortion Measures
Kernel methods have been used for turning linear learning algorithms into nonlinear ones. These nonlinear algorithms measure distances between data points by the distance in the kernel-induced feature space. In lossy data compression, the optimal tradeoff between the number of quantized points and t...
Main Author: | Kazuho Watanabe |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-07-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/19/7/336 |
Similar Items
-
On the Existence of (k,l)-Kernels in Infinite Digraphs: A Survey
by: Galeana-Sánchez H., et al.
Published: (2014-08-01) -
Rate Distortion Functions and Rate Distortion Function Lower Bounds for Real-World Sources
by: Jerry Gibson
Published: (2017-11-01) -
Adaptive Compensation of the Nonlinear Distortions in Optical Transmitters Using Predistortion
by: O. Panagiev
Published: (2008-12-01) -
TreeKernel: interpretable kernel machine tests for interactions between -omics and clinical predictors with applications to metabolomics and COPD phenotypes
by: Charlie M. Carpenter, et al.
Published: (2023-10-01) -
A Coding Theorem for f-Separable Distortion Measures
by: Yanina Shkel, et al.
Published: (2018-02-01)