Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference
Abstract
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.
Keywords
Cite
@article{arxiv.1901.05906,
title = {Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference},
author = {Xinyu Hu and Paul Szerlip and Theofanis Karaletsos and Rohit Singh},
journal= {arXiv preprint arXiv:1901.05906},
year = {2019}
}
Comments
Third workshop on Bayesian Deep Learning (NeurIPS 2018)