A Variant of Gaussian Process Dynamical Systems
This work addresses modeling challenges in high-dimensional sequences for fields like time-series analysis, but it appears incremental as a variant of existing GPDSs.
The authors tackled the problem of modeling high-dimensional sequential data by proposing a collaborative multi-output Gaussian process dynamical system (CGPDS), which captures dependencies among dimensions while maintaining unique characteristics, using inducing points and stochastic variational inference for training and prediction.
In order to better model high-dimensional sequential data, we propose a collaborative multi-output Gaussian process dynamical system (CGPDS), which is a novel variant of GPDSs. The proposed model assumes that the output on each dimension is controlled by a shared global latent process and a private local latent process. Thus, the dependence among different dimensions of the sequences can be captured, and the unique characteristics of each dimension of the sequences can be maintained. For training models and making prediction, we introduce inducing points and adopt stochastic variational inference methods.