SOURCE-LINKED INTELLIGENCE

TEMPER: Temporal Encoder-Masked Probabilistic Ensemble Regressor for Time-Series Forecasting

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Probabilistic forecasting requires accurate central predictions and calibrated uncertainty estimates. This paper presents TEMPER, the Temporal Encoder-Masked Probabilistic Ensemble Regressor, a univariate time-series forecasting algorithm that combines a temporal autoencoder, a differentiable masked neural decision forest, continuous ranked probability score (CRPS) training, and Gaussian-mixture post-processing. The R implementation is built on torch for R and returns horizon-wise density, distribution, quantile, and sampler functions. We evaluate TEMPER on three deterministic synthetic level

Read original source ↗ Open in workspace

recordType

paper

region

Global