Naga: Vedic Encoding for Deep State Space Models

TL;DR

Naga introduces a Vedic-inspired bidirectional encoding for deep state space models, improving long-term time series forecasting accuracy and efficiency by capturing distant temporal dependencies.

Contribution

The paper proposes a novel Vedic mathematics-inspired encoding method for deep state space models, enhancing temporal dependency modeling in long-term time series forecasting.

Findings

Outperforms 28 state-of-the-art models on multiple benchmarks

Demonstrates improved efficiency over existing deep SSM approaches

Provides an interpretable, structured encoding for sequence modeling

Abstract

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.