arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.05906cs.LGstat.ML
收藏

应用SVGD于贝叶斯神经网络之周期性时间序列预测与推论

Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference

Columbia University(哥伦比亚大学);Uber AI Labs(优步人工智能实验室)

Xinyu Hu, Paul Szerlip, Theofanis Karaletsos, Rohit Singh

摘要:

提出了一种基于回归的BNN模型来预测具有校准不确定性的时空量,如小时乘客需求。本文的主要贡献是(一)前馈确定性神经网络(DetNN)的架构,预测周期性的时间序列数据与异常预测事件的敏感性;(二)贝叶斯框架应用SVGD训练大型神经网络等任务,能够产生时间序列预测以及周围的预测的不确定性措施。实验表明,与微调的多层感知器(MLP)相比,所提出的BNN在美国8个城市的平均估计误差降低了10%,比没有SVGD训练的相同网络架构好4%。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑