Characteristic kernels and infinitely divisible distributions

MaRDI QIDQ2834518zbMATH OpenFDO

Authors Yu Nishiyama, Kenji Fukumizu

Publication date 22 November 2016

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1403.7304, http://jmlr.csail.mit.edu/papers/v17/14-132.html

zbMATH Keywords

infinitely divisible distributionconjugate kernelcharacteristic kernelkernel meanconvolution trick

Mathematics Subject Classification ID

Infinitely divisible distributions; stable distributions (60E07) Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Kernel distribution embeddings: universal kernels, characteristic kernels and kernel metrics on distributions
• On infinite divisibility of convolution and mapping kernels
• Statistical inference with reproducing kernels
• Universality, Characteristic Kernels and RKHS Embedding of Measures
• Strictly proper kernel scores and characteristic kernels on compact spaces

Cited in

(6)

• Machine learning with kernels for portfolio valuation and risk management
• Learning rates for the kernel regularized regression with a differentiable strongly convex loss
• On infinite divisibility of convolution and mapping kernels
• Distribution free tests for model selection based on maximum mean discrepancy with estimated parameters
• Model-based kernel sum rule: kernel Bayesian inference with probabilistic models
• Complete Nevanlinna-Pick kernels and the characteristic function

This page was built for publication: Characteristic kernels and infinitely divisible distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2834518)