Timezone: »
We study learning curves for Gaussian process regression which characterise performance in terms of the Bayes error averaged over datasets of a given size. Whilst learning curves are in general very difficult to calculate we show that for discrete input domains, where similarity between input points is characterised in terms of a graph, accurate predictions can be obtained. These should in fact become exact for large graphs drawn from a broad range of random graph ensembles with arbitrary degree distributions where each input (node) is connected only to a finite number of others. The method is based on translating the appropriate belief propagation equations to the graph ensemble. We demonstrate the accuracy of the predictions for Poisson (ErdosRenyi) and regular random graphs, and discuss when and why previous approximations to the learning curve fail.
Author Information
Matthew J Urry (King's College London)
Peter Sollich (King's College London)
Related Events (a corresponding poster, oral, or spotlight)

2010 Poster: Exact learning curves for Gaussian process regression on large random graphs »
Tue Dec 7th 08:00  08:00 AM Room None
More from the Same Authors

2015 Workshop: Modelling and inference for dynamics on complex interaction networks: joining up machine learning and statistical physics »
Manfred Opper · Yasser Roudi · Peter Sollich 
2012 Poster: Learning curves for multitask Gaussian process regression »
Peter Sollich · Simon R Ashton 
2009 Poster: Kernels and learning curves for Gaussian process regression on random graphs »
Peter Sollich · Matthew J Urry · Camille Coti 
2009 Spotlight: Kernels and learning curves for Gaussian process regression on random graphs »
Peter Sollich · Matthew J Urry · Camille Coti