Multi-period Time Series Modeling with Sparsity via Bayesian Variational Inference

Abstract

In this paper, we use augmented the hierarchical latent variable model to model multi-period time series, where the dynamics of time series are governed by factors or trends in multiple periods. Previous methods based on stacked recurrent neural network (RNN) and deep belief network (DBN) models cannot model the tendencies in multiple periods, and no models for sequential data pay special attention to redundant input variables which have no or even negative impact on prediction and modeling. Applying hierarchical latent variable model with multiple transition periods, our proposed algorithm can capture dependencies in different temporal resolutions. Introducing Bayesian neural network with Horseshoe prior as input network, we can discard the redundant input variables in the optimization process, concurrently with the learning of other parts of the model. Based on experiments with both synthetic and real-world data, we show that the proposed method significantly improves the modeling and prediction performance on multi-period time series.

References in corpus (3)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Bayesian Compression for Deep Learning
• Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors

Cited by in corpus (7)

• Conditional Time Series Forecasting with Convolutional Neural Networks
• Recurrent Neural Networks for Time Series Forecasting
• Surrogate Optimization of Deep Neural Networks for Groundwater Predictions
• seq2graph: Discovering Dynamic Dependencies from Multivariate Time Series with Multi-level Attention
• Enhancing Operation of a Sewage Pumping Station for Inter Catchment Wastewater Transfer by Using Deep Learning and Hydraulic Model
• DeepCSO: Forecasting of Combined Sewer Overflow at a Citywide Level using Multi-task Deep Learning
• Forecasting solar radiation during dust storms using deep learning