Naga: Vedic Encoding for Deep State Space Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schaller, Melanie, Janssen, Nick, Rosenhahn, Bodo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917085689413632
author Schaller, Melanie
Janssen, Nick
Rosenhahn, Bodo
author_facet Schaller, Melanie
Janssen, Nick
Rosenhahn, Bodo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13510
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Naga: Vedic Encoding for Deep State Space Models
Schaller, Melanie
Janssen, Nick
Rosenhahn, Bodo
Machine Learning
Artificial Intelligence
Systems and Control
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.
title Naga: Vedic Encoding for Deep State Space Models
topic Machine Learning
Artificial Intelligence
Systems and Control
url https://arxiv.org/abs/2511.13510