Bayesian wavelet de-noising with the caravan prior

Abstract

According to both domain expert knowledge and empirical evidence, wavelet coefficients of real signals tend to exhibit clustering patterns, in that they contain connected regions of coefficients of similar magnitude (large or small). A wavelet de-noising approach that takes into account such a feature of the signal may in practice outperform other, more vanilla methods, both in terms of the estimation error and visual appearance of the estimates. Motivated by this observation, we present a Bayesian approach to wavelet de-noising, where dependencies between neighbouring wavelet coefficients are a priori modelled via a Markov chain-based prior, that we term the caravan prior. Posterior computations in our method are performed via the Gibbs sampler. Using representative synthetic and real data examples, we conduct a detailed comparison of our approach with a benchmark empirical Bayes denoising method (due to Johnstone and Silverman). We show that the caravan prior fares well and is therefore a useful addition to the wavelet de-noising toolbox.

Bayesian nonparametric estimation in the current status continuous mark model

“…On the contrary, as we will show in the numerical examples, for the LNGL‐prior, this overparametrization can be substantially balanced/regularized by equipping the parameter with a prior distribution. The idea of histogram‐type priors with positively correlated adjacent bins has recently been used successfully in other settings as well, see for instance Gugushvili et al (2018), Gugushvili et al (2019).…”

Fast and scalable non-parametric Bayesian inference for Poisson point processes

“…As a side remark, we note that estimation of discontinuous functions might be a delicate matter with the GMC prior. See Gugushvili et al (2019a) for further remarks.…”