Naga: Vedic Encoding for Deep State Space Models
This work addresses long-range sequence modeling for time series forecasting, offering an interpretable and efficient alternative, though it appears incremental as it builds on existing deep SSM approaches.
The paper tackles long-term time series forecasting by proposing Naga, a deep State Space Model encoding inspired by Vedic mathematics, which outperforms 28 state-of-the-art models on benchmarks like ETTh1 and Weather, showing improved efficiency.
This paper presents Naga, a deep State Space Model (SSM) encoding approach inspired by structural concepts from Vedic mathematics. The proposed method introduces a bidirectional representation for time series by jointly processing forward and time-reversed input sequences. These representations are then combined through an element-wise (Hadamard) interaction, resulting in a Vedic-inspired encoding that enhances the model's ability to capture temporal dependencies across distant time steps. We evaluate Naga on multiple long-term time series forecasting (LTSF) benchmarks, including ETTh1, ETTh2, ETTm1, ETTm2, Weather, Traffic, and ILI. The experimental results show that Naga outperforms 28 current state of the art models and demonstrates improved efficiency compared to existing deep SSM-based approaches. The findings suggest that incorporating structured, Vedic-inspired decomposition can provide an interpretable and computationally efficient alternative for long-range sequence modeling.