Characterizing Deep Gaussian Processes via Nonlinear Recurrence Systems
This work addresses a key limitation in DGPs for researchers and practitioners in machine learning, offering incremental theoretical insights into their behavior.
The paper tackled the pathology of Deep Gaussian Processes (DGPs) where learning capacity decreases with more layers, by analyzing them as nonlinear dynamic systems and deriving recurrence relations for four common stationary kernel functions, providing a tighter bound and convergence rate.
Recent advances in Deep Gaussian Processes (DGPs) show the potential to have more expressive representation than that of traditional Gaussian Processes (GPs). However, there exists a pathology of deep Gaussian processes that their learning capacities reduce significantly when the number of layers increases. In this paper, we present a new analysis in DGPs by studying its corresponding nonlinear dynamic systems to explain the issue. Existing work reports the pathology for the squared exponential kernel function. We extend our investigation to four types of common stationary kernel functions. The recurrence relations between layers are analytically derived, providing a tighter bound and the rate of convergence of the dynamic systems. We demonstrate our finding with a number of experimental results.