VAEneu: A New Avenue for VAE Application on Probabilistic Forecasting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914787298902016 |
|---|---|
| author | Koochali, Alireza Tahaei, Ensiye Dengel, Andreas Ahmed, Sheraz |
| author_facet | Koochali, Alireza Tahaei, Ensiye Dengel, Andreas Ahmed, Sheraz |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_04252 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VAEneu: A New Avenue for VAE Application on Probabilistic Forecasting Koochali, Alireza Tahaei, Ensiye Dengel, Andreas Ahmed, Sheraz Machine Learning Artificial Intelligence 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. |
| title | VAEneu: A New Avenue for VAE Application on Probabilistic Forecasting |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2405.04252 |