Recurrent Neural Processes
This work addresses time-series modeling challenges for applications like system identification, but it is incremental as it builds on existing Neural Processes.
The authors tackled the problem of modeling sequential data with slow long-term variabilities by extending Neural Processes to Recurrent Neural Processes (RNPs), a family of conditional state space models. They demonstrated that RNPs improve predictive performance on real-world time-series data and nonlinear system identification, even with limited data availability.
We extend Neural Processes (NPs) to sequential data through Recurrent NPs or RNPs, a family of conditional state space models. RNPs model the state space with Neural Processes. Given time series observed on fast real-world time scales but containing slow long-term variabilities, RNPs may derive appropriate slow latent time scales. They do so in an efficient manner by establishing conditional independence among subsequences of the time series. Our theoretically grounded framework for stochastic processes expands the applicability of NPs while retaining their benefits of flexibility, uncertainty estimation, and favorable runtime with respect to Gaussian Processes (GPs). We demonstrate that state spaces learned by RNPs benefit predictive performance on real-world time-series data and nonlinear system identification, even in the case of limited data availability.