Hyperbolic Time Series Forecasting with Learnable Decomposition and Manifold Dynamics
Proposed HyperForecast is the first long-term time series forecasting (LTSF) framework operating in hyperbolic space and consistently outperforms existing and state-of-the-art baselines on 9 of 11 long-term forecasting benchmarks, achieving up to 58% lower mean squared error at long horizons.
Sarang Rajendra Patil, Vishal Fenn, Meng-Jia Xu
· 0 citations