Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference
This work addresses uncertainty quantification in time-series forecasting for applications like urban mobility, but it is incremental as it applies an existing method (SVGD) to a specific domain.
The paper tackled the problem of predicting cyclical time-series data, such as hourly rider demand, with calibrated uncertainties, and achieved a 10% reduction in average estimation error compared to a fine-tuned MLP across 8 U.S. cities.
A regression-based BNN model is proposed to predict spatiotemporal quantities like hourly rider demand with calibrated uncertainties. The main contributions of this paper are (i) A feed-forward deterministic neural network (DetNN) architecture that predicts cyclical time series data with sensitivity to anomalous forecasting events; (ii) A Bayesian framework applying SVGD to train large neural networks for such tasks, capable of producing time series predictions as well as measures of uncertainty surrounding the predictions. Experiments show that the proposed BNN reduces average estimation error by 10% across 8 U.S. cities compared to a fine-tuned multilayer perceptron (MLP), and 4% better than the same network architecture trained without SVGD.