EnTransformer: A Deep Generative Transformer for Multivariate Probabilistic Forecasting

ArXi:2603.11909v1 Announce Type: cross Reliable uncertainty quantification is critical in multivariate time series forecasting problems arising in domains such as energy systems and transportation networks, among many others. Although Transformer-based architectures have recently achieved strong performance for sequence modeling, most probabilistic forecasting approaches rely on restrictive parametric likelihoods or quantile-based objectives. They can struggle to capture complex joint predictive distributions across multiple correlated time series.