Metraipolis › archive › dc_dc693fbd10e9

On the Cardinality of Optimal Representations in the Binary-Source Information Bottleneck — arXiv:2610.06627

Source
arXiv
Original
https://arxiv.org/abs/2610.06627
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:32.796Z
SHA-256 of the archived text
f730b65b844fc78c5be26783c754d979d636c7a44d6962c378a4167c5849bd73
Stable URL of this page
https://metraipolis.com/documento/dc_dc693fbd10e9

How to cite

On the Cardinality of Optimal Representations in the Binary-Source Information Bottleneck — arXiv:2610.06627 — arXiv, https://arxiv.org/abs/2610.06627 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc693fbd10e9 (Metraipolis archive dc_dc693fbd10e9, sha256 f730b65b844fc78c5be26783c754d979d636c7a44d6962c378a4167c5849bd73)
BibTeX
@misc{dcdc693fbd10e9,
  title = {On the Cardinality of Optimal Representations in the Binary-Source Information Bottleneck — arXiv:2610.06627},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06627},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc693fbd10e9; sha256 f730b65b844fc78c5be26783c754d979d636c7a44d6962c378a4167c5849bd73},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06627. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The information bottleneck (IB) seeks a representation $U$ of a source $X$ that retains as much information as possible about a target $Y$, subject to a constraint on $I(U;X)$. A classical argument shows that it suffices to consider representations with at most $|\mathcal{X}|+1$ symbols, and this bound is known to be tight whenever $|\mathcal{X}| \geq 3$. We show that the binary case behaves differently: if $X$ is binary and $Y$ is finite, then for every joint distribution of $(X,Y)$ and every rate constraint, the IB optimum is attained by a binary $U$. Hence the bound $|\mathcal{U}| \leq |\mathcal{X}|+1$ sharpens to $|\mathcal{U}| \leq |\mathcal{X}|$ for binary sources. The proof combines a separating hyperplane argument with the observation that, for a binary source, the ratio of the second derivatives of the two entropy functions involved is concave.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Information Theory (cs.IT) ; Machine Learning (cs.LG); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.06627 — 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 2026-10-06T05:27:06.044Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).