Online Fine-Tuning of Carbon Emission Predictions using Real-Time Recurrent Learning for State Space Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lemmel, Julian, Kranzl, Manuel, Lamine, Adam, Neubauer, Philipp, Grosu, Radu, Neubauer, Sophie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912902917652480
author Lemmel, Julian
Kranzl, Manuel
Lamine, Adam
Neubauer, Philipp
Grosu, Radu
Neubauer, Sophie
author_facet Lemmel, Julian
Kranzl, Manuel
Lamine, Adam
Neubauer, Philipp
Grosu, Radu
Neubauer, Sophie
contents This paper introduces a new approach for fine-tuning the predictions of structured state space models (SSMs) at inference time using real-time recurrent learning. While SSMs are known for their efficiency and long-range modeling capabilities, they are typically trained offline and remain static during deployment. Our method enables online adaptation by continuously updating model parameters in response to incoming data. We evaluate our approach for linear-recurrent-unit SSMs using a small carbon emission dataset collected from embedded automotive hardware. Experimental results show that our method consistently reduces prediction error online during inference, demonstrating its potential for dynamic, resource-constrained environments.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00804
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Online Fine-Tuning of Carbon Emission Predictions using Real-Time Recurrent Learning for State Space Models
Lemmel, Julian
Kranzl, Manuel
Lamine, Adam
Neubauer, Philipp
Grosu, Radu
Neubauer, Sophie
Computational Engineering, Finance, and Science
Machine Learning
Systems and Control
This paper introduces a new approach for fine-tuning the predictions of structured state space models (SSMs) at inference time using real-time recurrent learning. While SSMs are known for their efficiency and long-range modeling capabilities, they are typically trained offline and remain static during deployment. Our method enables online adaptation by continuously updating model parameters in response to incoming data. We evaluate our approach for linear-recurrent-unit SSMs using a small carbon emission dataset collected from embedded automotive hardware. Experimental results show that our method consistently reduces prediction error online during inference, demonstrating its potential for dynamic, resource-constrained environments.
title Online Fine-Tuning of Carbon Emission Predictions using Real-Time Recurrent Learning for State Space Models
topic Computational Engineering, Finance, and Science
Machine Learning
Systems and Control
url https://arxiv.org/abs/2508.00804