VAEneu: A New Avenue for VAE Application on Probabilistic Forecasting
Not on the map. Why?
Abstract (arXiv)
This paper presents VAEneu, an innovative autoregressive method for multistep ahead univariate probabilistic time series forecasting. We employ the conditional VAE framework and optimize the lower bound of the predictive distribution likelihood function by adopting the Continuous Ranked Probability Score (CRPS), a strictly proper scoring rule, as the loss function. This novel pipeline results in forecasting sharp and well-calibrated predictive distribution. Through a comprehensive empirical study, VAEneu is rigorously benchmarked against 12 baseline models across 12 datasets. The results unequivocally demonstrate VAEneu's remarkable forecasting performance. VAEneu provides a valuable tool for quantifying future uncertainties, and our extensive empirical study lays the foundation for future comparative studies for univariate multistep ahead probabilistic forecasting.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 40 of its 81 references that are in the map. First posted on arXiv 7 May 2024.
Builds on
40 of 81 references.
References · 40
- 2017Attention Is All You Needcited by 59,932
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2015Variational Inference with Normalizing Flowscited by 2,161
- 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
- 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
- 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
- 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
- 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
- 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
28 more
- 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 748
- 2018Deep learning for time series classification: a reviewcited by 575
- 2013Generating Sequences With Recurrent Neural Networkscited by 549
- 2016Input Convex Neural Networkscited by 407
- 2018Implicit Quantile Networks for Distributional Reinforcement Learningcited by 362
- 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 332
- 2021Monash Time Series Forecasting Archivecited by 256
- 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 232
- 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
- 2019High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processescited by 147
- 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 142
- 2018Neural networks for post-processing ensemble weather forecastscited by 95
- 2019Deep Factors for Forecastingcited by 86
- 2019Probabilistic Forecasting with Temporal Convolutional Neural Networkcited by 63
- 2017Improving Palliative Care with Deep Learningcited by 28
- 2018DeepDownscale: a Deep Learning Strategy for High-Resolution Weather Forecastcited by 28
- 2021Probabilistic Time Series Forecasting with Implicit Quantile Networkscited by 17
- 2019Probabilistic Forecasting of Sensory Data with Generative Adversarial Networks - ForGANcited by 16
- 2020If You Like It, GAN It. Probabilistic Multivariate Times Series Forecast With GANcited by 14
- 2018CRED: A Deep Residual Network of Convolutional and Recurrent Units for Earthquake Signal Detectioncited by 13
- 2018PhaseLink: A Deep Learning Approach to Seismic Phase Associationcited by 10
- 2018A Multi-Scheme Ensemble Using Coopetitive Soft-Gating With Application to Power Forecasting for Renewable Energy Generationcited by 3
- 2018Benchmarking Deep Sequential Models on Volatility Predictions for Financial Time Seriescited by 3
- 2019ML for Flood Forecasting at Scalecited by 3
- 2017Approximate Bayesian Forecastingcited by 2
- 2018Accurate, Data-Efficient Learning from Noisy, Choice-Based Labels for Inherent Risk Scoringcited by 1
- 2018Machine Learning on Electronic Health Records: Models and Features Usages to predict Medication Non-Adherencecited by 1
- 2018Predicting Inpatient Discharge Prioritization With Electronic Health Recordscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.