Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nochumsohn, Liran, Marshanski, Raz, Zisling, Hedi, Azencot, Omri
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917521284661248
author Nochumsohn, Liran
Marshanski, Raz
Zisling, Hedi
Azencot, Omri
author_facet Nochumsohn, Liran
Marshanski, Raz
Zisling, Hedi
Azencot, Omri
contents Time series forecasting (TSF) is critical in domains like energy, finance, healthcare, and logistics, requiring models that generalize across diverse datasets. Large pre-trained models such as Chronos and Time-MoE show strong zero-shot (ZS) performance but suffer from high computational costs. In this work, we introduce Super-Linear, a lightweight and scalable mixture-of-experts (MoE) model for general forecasting. It replaces deep architectures with simple frequency-specialized linear experts, trained on resampled data across multiple frequency regimes. A lightweight spectral gating mechanism dynamically selects relevant experts, enabling efficient, accurate forecasting. Despite its simplicity, Super-Linear demonstrates strong performance across benchmarks, while substantially improving efficiency, robustness to sampling rates, and interpretability. The implementation of Super-Linear is available at: \href{https://github.com/azencot-group/SuperLinear}{https://github.com/azencot-group/SuperLinear}.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15105
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting
Nochumsohn, Liran
Marshanski, Raz
Zisling, Hedi
Azencot, Omri
Machine Learning
Time series forecasting (TSF) is critical in domains like energy, finance, healthcare, and logistics, requiring models that generalize across diverse datasets. Large pre-trained models such as Chronos and Time-MoE show strong zero-shot (ZS) performance but suffer from high computational costs. In this work, we introduce Super-Linear, a lightweight and scalable mixture-of-experts (MoE) model for general forecasting. It replaces deep architectures with simple frequency-specialized linear experts, trained on resampled data across multiple frequency regimes. A lightweight spectral gating mechanism dynamically selects relevant experts, enabling efficient, accurate forecasting. Despite its simplicity, Super-Linear demonstrates strong performance across benchmarks, while substantially improving efficiency, robustness to sampling rates, and interpretability. The implementation of Super-Linear is available at: \href{https://github.com/azencot-group/SuperLinear}{https://github.com/azencot-group/SuperLinear}.
title Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2509.15105