Paper announcement: the Relevance Vector Machine

[Michael Tipping]

Dear Connectionists,

A paper on the "relevance vector machine", a Bayesian implementation of
sparse kernel regression and classification models (which is to appear in
the forthcoming proceedings of NIPS*12), is now available online:

ftp://ftp.research.microsoft.com/users/mtipping/rvm_nips.ps.gz

Title and abstract are below:

--------------------------------------------------------------------------

			The Relevance Vector Machine

				Michael E. Tipping

The support vector machine (SVM) is a state-of-the-art technique for
regression and classification, combining excellent generalisation
properties with a sparse kernel representation. However, it does suffer
from a number of disadvantages, notably the absence of probabilistic
outputs, the requirement to estimate a trade-off parameter and the
need to utilise 'Mercer' kernel functions.  In this paper we
introduce the Relevance Vector Machine (RVM), a Bayesian
treatment of a generalised linear model of identical functional form
to the SVM.  The RVM suffers from none of the above disadvantages,
and examples demonstrate that for comparable generalisation
performance, the RVM requires dramatically fewer kernel functions.