DeRegiME: Deep Regime Mixtures for Probabilistic Forecasting under Distribution Shift

arXiv:2605. 19231v1 Announce Type: cross Abstract: We introduce DeRegiME -- Deep Regime Mixture of Experts -- a direct multi-horizon probabilistic forecaster that separates latent uncertainty regimes from the underlying signal and softly assigns each forecast location to learned recurring regimes using a sparse variational Gaussian process (GP) whose nonstationary regime-mixing kernel and Student-t likelihood combine per-regime sub-kernels and noise processes via a shared gate.