CircuITS, a novel architecture for probabilistic IMTS forecasting based on sum-product networks (SPNs), is proposed, which is flexible in capturing intricate dependencies between time series channels while structurally guaranteeing valid joint distributions.
Christian Klötergens, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme· arXiv.org· 1 citation
A model-based measure is introduced that compares a channel-dependent (CD) model to its channel-independent (CI) variant and only lagged MI and the CD gain recover every planted coupling, a model-based measure that compares a channel-dependent model to its channel-independent variant.
Ibram Abdelmalak, Mischa Putzke, Jungmin Choi et al.· 0 citations
Two-stage Odd Residual Flows (TORF), a framework that decouples mean forecasting from uncertainty estimation, achieves state-of-the-art deterministic accuracy (NMAE) while providing strong density estimation performance (CRPS) on short and long-horizon forecasting.
Kiran Madhusudhanan, Christian Klötergens, Lars Schmidt-Thieme et al.· 0 citations
A simple procedure is described that unfolds the joint input-target sequence into overlapping sliding windows, randomly reorders a controlled fraction of them, and reconstructs the sequence by averaging across the overlaps, producing synthetic samples with controlled variation while limiting temporal distortion.
Jafar Bakhshaliyev, Johannes Burchert, Niels Landwehr et al.· 0 citations
