SGA: Uncertainty Quantification for Multi-Step Forecasting in Time Series Foundation Models
The proposed SGA first characterizes the topology of all potential forecast branches using a directed acyclic graph, such that the graph complexity bounds the uncertainty of multi-step TSFM forecasts, and then precisely measures the graph complexity by integrating both topological information and TSFM-inherent stochast...
Xin-Miao Hu, Shuang Liang, Cheng Feng et al.
· 0 citations