Green BOA: Determining the environmental break-even point for ML-based data compression

Caterina Doglioni; Thomas Elliott; Akshat Gupta; Hanzila Hussain; Sanjiban Sengupta; Zhengkai Sun

cs.LGAug 20, 2026

Green BOA: Determining the environmental break-even point for ML-based data compression

Authors: Caterina Doglioni, Thomas Elliott, Akshat Gupta, Hanzila Hussain, Sanjiban Sengupta, Zhengkai Sun

Organizations: University of Manchester Manchester, UK · CERN/University of Manchester Manchester, UK

Abstract

We summarise the outcome of two summer internship projects based at the University of Manchester, focused on the break-even point in terms of environmental sustainability for ML-based data compression algorithms. Using the example of a ML-based lossless compression algorithm, we compare estimates for the carbon-equivalent of the infrastructure needed for ML training and inference with the carbon-equivalent savings from reduced disk storage requirements, and discuss their break-even point.

Figures & tables

Figure 1. Results of the break-even analysis in terms of $CO_{2}$ -equivalent for ML-based data compression and subsequent displaced HDD/tape storage.

Energy-Efficient ML

Energy-efficient machine learning reduces the energy and environmental costs of training and inference while preserving useful model performance.

See all 257 papers

An Introduction to Compression-Based Machine Learning
Sep 18, 2026John Hurwitz, Edward Raff, Charles K. NicholasMinimum Description Length
University of Maryland, Baltimore County · CrowdStrike · Syracuse University
The Environmental Impacts of Language Model Training Keep Rising Now is the Time to Catch Impacts on the Rebound
Oct 10, 2025Clément Morand, Anne-Laure Ligozat, Aurélie NévéolEnergy-Efficient ML Life Cycle Assessment
STL · Université Paris-Saclay, CNRS, LISN · ENSIIE, LISN, STL +2
From Grey-Box to Green-Box: When can Physics-Informed Machine Learning Reduce Carbon Footprints in Structural Health Monitoring?
Sep 27, 2026Daisy R. Bradley, Nathan A. Hinchliffe, Daniel J. Pitchforth +2Energy-Efficient ML Physics-Informed ML
Dynamics Research Group, University of Sheffield, Sheffield, UK

Sep 18, 2026J/K move · Enter open · S save

An Introduction to Compression-Based Machine Learning

John Hurwitz, Edward Raff, Charles K. Nicholas

University of Maryland, Baltimore County · CrowdStrike · Syracuse University

Minimum Description Length

Open paper AskPDF arXiv

Any lossless compression algorithm (like gzip) may be converted into a machine learning method, via either Normalized Compression Distance or the Minimum Description Length principle. Any auto-regressive model may be converted into a lossless compression method via entropy coding. This seemingly circular dependence has unrealized potential in modern artificial intelligence and machine learning, and we survey and formalize the various strategies that have been used to leverage compression for machine learning. We introduce and empirically validate a design framework for compression-based ML, finding compression-based methods competitive with conventional baselines and decisively stronger on malware. We find that varying these design choices yields accuracy gains of up to 0.62.

Abstract

Energy-Efficient ML

Explore similar work

An Introduction to Compression-Based Machine Learning

The Environmental Impacts of Language Model Training Keep Rising Now is the Time to Catch Impacts on the Rebound

From Grey-Box to Green-Box: When can Physics-Informed Machine Learning Reduce Carbon Footprints in Structural Health Monitoring?