Probabilistic Time Series Forecasting with Implicit Quantile Networks

Abstract

Here, we propose a general method for probabilistic time series forecasting. We combine an autoregressive recurrent neural network to model temporal dynamics with Implicit Quantile Networks to learn a large class of distributions over a time-series target. When compared to other probabilistic neural forecasting models on real- and simulated data, our approach is favorable in terms of point-wise prediction accuracy as well as on estimating the underlying temporal distribution.

arXiv commentAccepted at the ICML 2021 Time Series Workshop

References in corpus (7)

• Deep Learning in Neural Networks: An Overview
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Deep and Confident Prediction for Time Series at Uber
• Fully Parameterized Quantile Function for Distributional Reinforcement Learning
• Autoregressive Quantile Networks for Generative Modeling

Cited by in corpus (3)

• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
• Real-Time Decision-Making for Digital Twin in Additive Manufacturing with Model Predictive Control using Time-Series Deep Neural Networks
• Implicit Quantile Networks For Emulation in Jet Physics