Metraipolis › archive › dc_7a4ca77534fd

On the Information Bottleneck for Stable Variables — arXiv:2610.08007

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08007
License (as archived)
CC0-1.0
Archived
2026-10-07T12:10:20.308Z
SHA-256 of the archived text
bb957b4b7daec9bf3f41668fafb84870427693f0d7aa060521df6d4f2efa45d3
Stable URL of this page
https://metraipolis.com/documento/dc_7a4ca77534fd

How to cite

On the Information Bottleneck for Stable Variables — arXiv:2610.08007 — arXiv (en), https://arxiv.org/abs/2610.08007 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a4ca77534fd (Metraipolis archive dc_7a4ca77534fd, sha256 bb957b4b7daec9bf3f41668fafb84870427693f0d7aa060521df6d4f2efa45d3)
BibTeX
@misc{dc7a4ca77534fd,
  title = {On the Information Bottleneck for Stable Variables — arXiv:2610.08007},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08007},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a4ca77534fd; sha256 bb957b4b7daec9bf3f41668fafb84870427693f0d7aa060521df6d4f2efa45d3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08007. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We consider a generalization of the Gaussian information bottleneck problem to jointly stable variables $X$ and $Y$. Specifically, for $X = Y + A$, where $A$ is stable and independent of $Y$, we find optimal stochastic linear encoders of the form $T = kX + N$, $N$ being stable and independent of $X$. We characterize the linear stable information bottleneck in closed-form and its critical value. Furthermore, we show that, except for the Gaussian case, such stochastic linear encoders are strictly suboptimal, however asymptotically optimal at large compression rate. Our linear solution recovers the Gaussian information bottleneck for jointly Gaussian variables.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.IT, nuovi lavori del giorno).
Categorie arXiv: Information Theory (cs.IT).
Pagina del lavoro: https://arxiv.org/abs/2610.08007 — 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 2026-10-07T11:42:17.267Z dalla pagina https://arxiv.org/list/math.IT/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).