Saved in:
Bibliographic Details
Main Author: Gogoi, Shakhyar
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.20772
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908794231980032
author Gogoi, Shakhyar
author_facet Gogoi, Shakhyar
contents COMET-SG1 is a lightweight, stability-oriented autoregressive regression model designed for time-series prediction on edge and embedded AI systems. Unlike recurrent neural networks or transformer-based sequence models, COMET-SG1 operates through linear behavior-space encoding, memory-anchored transition estimation, and deterministic state updates. This structure prioritizes bounded long-horizon behavior under fully autoregressive inference, a critical requirement for edge deployment where prediction errors accumulate over time. Experiments on non-stationary synthetic time-series data demonstrate that COMET-SG1 achieves competitive short-horizon accuracy while exhibiting significantly reduced long-horizon drift compared to MLP, LSTM, and k-nearest neighbor baselines. With a compact parameter footprint and operations compatible with fixed-point arithmetic, COMET-SG1 provides a practical and interpretable approach for stable autoregressive prediction in edge and embedded AI applications.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20772
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle COMET-SG1: Lightweight Autoregressive Regressor for Edge and Embedded AI
Gogoi, Shakhyar
Machine Learning
COMET-SG1 is a lightweight, stability-oriented autoregressive regression model designed for time-series prediction on edge and embedded AI systems. Unlike recurrent neural networks or transformer-based sequence models, COMET-SG1 operates through linear behavior-space encoding, memory-anchored transition estimation, and deterministic state updates. This structure prioritizes bounded long-horizon behavior under fully autoregressive inference, a critical requirement for edge deployment where prediction errors accumulate over time. Experiments on non-stationary synthetic time-series data demonstrate that COMET-SG1 achieves competitive short-horizon accuracy while exhibiting significantly reduced long-horizon drift compared to MLP, LSTM, and k-nearest neighbor baselines. With a compact parameter footprint and operations compatible with fixed-point arithmetic, COMET-SG1 provides a practical and interpretable approach for stable autoregressive prediction in edge and embedded AI applications.
title COMET-SG1: Lightweight Autoregressive Regressor for Edge and Embedded AI
topic Machine Learning
url https://arxiv.org/abs/2601.20772