Posterior contraction rates for constrained deep Gaussian processes in density estimation and classication

Abstract

We provide posterior contraction rates for constrained deep Gaussian processes in non-parametric density estimation and classication. The constraints are in the form of bounds on the values and on the derivatives of the Gaussian processes in the layers of the composition structure. The contraction rates are rst given in a general framework, in terms of a new concentration function that we introduce and that takes the constraints into account. Then, the general framework is applied to integrated Brownian motions, Riemann-Liouville processes, and Mat{é}rn processes and to standard smoothness classes of functions. In each of these examples, we can recover known minimax rates.

References in corpus (5)

• Rates of contraction of posterior distributions based on Gaussian process priors
• Deep Gaussian Processes
• Adaptive Bayesian estimation using a Gaussian random field with inverse Gamma bandwidth
• Reproducing kernel Hilbert spaces of Gaussian priors
• Calibration and improved prediction of computer models by universal Kriging