Metraipolis › archive › dc_cae97e8809a4
An Introduction to Compression-Based Machine Learning — arXiv:2609.21309
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.21309
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T01:44:57.776Z
- SHA-256 of the archived text
39018a2d5527b2f7c348e29bd8c01f9d4836fdc7521cdf9a1cdf0a3e0e65f8d4- Stable URL of this page
https://metraipolis.com/documento/dc_cae97e8809a4
How to cite
An Introduction to Compression-Based Machine Learning — arXiv:2609.21309 — arXiv (en), https://arxiv.org/abs/2609.21309 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cae97e8809a4 (Metraipolis archive dc_cae97e8809a4, sha256 39018a2d5527b2f7c348e29bd8c01f9d4836fdc7521cdf9a1cdf0a3e0e65f8d4)
BibTeX
@misc{dccae97e8809a4,
title = {An Introduction to Compression-Based Machine Learning — arXiv:2609.21309},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.21309},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cae97e8809a4; sha256 39018a2d5527b2f7c348e29bd8c01f9d4836fdc7521cdf9a1cdf0a3e0e65f8d4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21309. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.21309 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T01:14:16.623Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).