arXiv Analytics

Sign in

arXiv:1809.07347 [cs.LG]AbstractReferencesReviewsResources

A Generalized Representer Theorem for Hilbert Space - Valued Functions

Sanket Diwale, Colin Jones

Published 2018-09-19Version 1

The necessary and sufficient conditions for existence of a generalized representer theorem are presented for learning Hilbert space-valued functions. Representer theorems involving explicit basis functions and Reproducing Kernels are a common occurrence in various machine learning algorithms like generalized least squares, support vector machines, Gaussian process regression and kernel based deep neural networks to name a few. Due to the more general structure of the underlying variational problems, the theory is also relevant to other application areas like optimal control, signal processing and decision making. We present the generalized representer as a unified view for supervised and semi-supervised learning methods, using the theory of linear operators and subspace valued maps. The implications of the theorem are presented with examples of multi input-multi output regression, kernel based deep neural networks, stochastic regression and sparsity learning problems as being special cases in this unified view.

Related articles: Most relevant | Search more
arXiv:1711.02114 [cs.LG] (Published 2017-11-06)
Bounding and Counting Linear Regions of Deep Neural Networks
arXiv:1706.05098 [cs.LG] (Published 2017-06-15)
An Overview of Multi-Task Learning in Deep Neural Networks
arXiv:1708.01911 [cs.LG] (Published 2017-08-06)
Training of Deep Neural Networks based on Distance Measures using RMSProp