A Generalized Representer Theorem for Hilbert Space - Valued Functions
This work offers a foundational theoretical framework for researchers in machine learning and related domains, though it is incremental in extending representer theorems to more general settings.
The paper tackles the problem of establishing necessary and sufficient conditions for a generalized representer theorem for learning Hilbert space-valued functions, providing a unified framework that applies to various machine learning algorithms and other fields like optimal control and signal processing.
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.