VAEneu: A New Avenue for VAE Application on Probabilistic Forecasting

arXiv:2405.04252v1 Announce Type: new
Abstract: 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 …

abstract application arxiv autoregressive continuous cs.ai cs.lg distribution forecasting framework function likelihood paper predictive probability scoring series time series time series forecasting type vae