摘要：We consider a fully Bayesian treatment of radial basis functionregression, and propose a solution to the the instability of basis selection.Indeed, when bases are selected solely according to the magnitude of theirposterior inclusion probabilities, it is often the case that many bases inthe same neighborhood end up getting selected leading to redundancy andultimately inaccuracy of the representation. In this paper, we propose astraightforward solution to the problem based on post-processing the samplepath yielded by the model space search technique. Speci cally, we performan a posteriori model-based clustering of the sample path via a mixture ofGaussians, and then select the points closer to the means of the Gaussians.Our solution is found to be more stable and yields a better performance onsimulated and real tasks.
关键词：High-dimensional function approximation; radial basis functions;kernels; optimal prediction; Bayesian model selection; mixture modelling.
