Metraipolis › archive › dc_4fc030a0e947
Neural Compression over Equivalence Classes: Exact Gauges and Functional Rate-Distortion — arXiv:2611.07233
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07233
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:44:11.301Z
- SHA-256 of the archived text
28822786625b8d409b6e6e3ca9762bb82823598ae84a2c0026ea235558b270de- Stable URL of this page
https://metraipolis.com/documento/dc_4fc030a0e947
How to cite
Neural Compression over Equivalence Classes: Exact Gauges and Functional Rate-Distortion — arXiv:2611.07233 — arXiv (en), https://arxiv.org/abs/2611.07233 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fc030a0e947 (Metraipolis archive dc_4fc030a0e947, sha256 28822786625b8d409b6e6e3ca9762bb82823598ae84a2c0026ea235558b270de)
BibTeX
@misc{dc4fc030a0e947,
title = {Neural Compression over Equivalence Classes: Exact Gauges and Functional Rate-Distortion — arXiv:2611.07233},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07233},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fc030a0e947; sha256 28822786625b8d409b6e6e3ca9762bb82823598ae84a2c0026ea235558b270de},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07233. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural networks admit many parameterizations of the same or nearly the same function, but deployment typically stores whichever parameter vector training happens to produce. We show that this representational freedom can itself be used for compression. Rather than redesigning the codec, we search over exact function-preserving transformations and controlled functional perturbations, using the unchanged physical compressor itself to select cheaper representations. Exact gauge families provide a zero-distortion reference under the strict audit; allowing small functional changes exposes much larger rate-distortion gains. Across SmolLM2 and Qwen3, our method reduces Zstandard-compressed checkpoint size by up to 23.4\%, with similar relative reductions under gzip, Brotli, and ZipNN, establishing trained-network representational freedom as a practical storage resource. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.07233 — 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 2026-11-06T14:21:42.618Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).