Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Preprints and Working Papers
  4. A Generalized Representer Theorem for Hilbert Space - Valued Functions
 
working paper

A Generalized Representer Theorem for Hilbert Space - Valued Functions

Diwale, Sanket Sanjay  
•
Jones, Colin  
2019

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. The following presents a generalized representer theorem using the theory of closed, densely defined linear operators and subspace valued maps as a means to address variational optimization problems in learning and control. The implications of the theorem are presented with examples of multi-input - multi-output problems from kernel-based deep neural networks, stochastic regression and sparsity learning problems.

  • Files
  • Details
  • Metrics
Type
working paper
Author(s)
Diwale, Sanket Sanjay  
Jones, Colin  
Date Issued

2019

Subjects

dense linear operators

•

adjoints

•

kernels

•

representer theorems

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
LA3  
Available on Infoscience
April 30, 2019
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/156180
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés