A General Framework for Uncertainty Quantification via Neural SDE-RNN
This addresses the problem of reliable uncertainty estimation in time series data for applications like power systems, though it appears incremental as it builds on existing neural SDE and RNN concepts.
The paper tackles the challenge of uncertainty quantification in deep learning for time series imputation with irregularly sampled measurements by proposing a framework based on recurrent neural networks and neural stochastic differential equations, achieving results that outperform state-of-the-art approaches on the IEEE 37 bus test distribution system.
Uncertainty quantification is a critical yet unsolved challenge for deep learning, especially for the time series imputation with irregularly sampled measurements. To tackle this problem, we propose a novel framework based on the principles of recurrent neural networks and neural stochastic differential equations for reconciling irregularly sampled measurements. We impute measurements at any arbitrary timescale and quantify the uncertainty in the imputations in a principled manner. Specifically, we derive analytical expressions for quantifying and propagating the epistemic and aleatoric uncertainty across time instants. Our experiments on the IEEE 37 bus test distribution system reveal that our framework can outperform state-of-the-art uncertainty quantification approaches for time-series data imputations.