d554f7bb7be44a7267068a7df88ddd20-Reviews.html

Summary: The paper proposes a multivariate stochastic process for modeling time series which incorporates locally varying smoothness in the mean and in the covariance matrix. The process uses latent dictionary functions with nested Gaussian process priors; the dictionary functions are linearly related to the observations through a sparse mapping. The authors outline MCMC and online algorithms for approximate Bayesian inference and assess performances using simulation and processing of financial data. Quality: The paper extends the application of the nested Gaussian process priors in [23] to the multivariate case and employs them for both the mean and covariance. This constitutes a sensible extension, and the authors develop an effective inference algorithm.