Metraipolis › archive › dc_96ad2eceac3a
When Information Is Not Enough: Accuracy-Constrained Thermodynamic Costs of Binary Classification — arXiv:2610.00291
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00291
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T17:48:01.296Z
- SHA-256 of the archived text
00cb6539ca70e6b61fbd63ae033f00570227f081abcf1b69cbc39e4ae803aad7- Stable URL of this page
https://metraipolis.com/documento/dc_96ad2eceac3a
How to cite
When Information Is Not Enough: Accuracy-Constrained Thermodynamic Costs of Binary Classification — arXiv:2610.00291 — arXiv (en), https://arxiv.org/abs/2610.00291 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96ad2eceac3a (Metraipolis archive dc_96ad2eceac3a, sha256 00cb6539ca70e6b61fbd63ae033f00570227f081abcf1b69cbc39e4ae803aad7)
BibTeX
@misc{dc96ad2eceac3a,
title = {When Information Is Not Enough: Accuracy-Constrained Thermodynamic Costs of Binary Classification — arXiv:2610.00291},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00291},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96ad2eceac3a; sha256 00cb6539ca70e6b61fbd63ae033f00570227f081abcf1b69cbc39e4ae803aad7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00291. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
How much entropy must a physical classifier produce to achieve a prescribed accuracy? Rate--distortion theory specifies the minimum information required, but does that information threshold suffice to determine the physical cost? We show that it does not, even for a binary task and a two-state memory. For a uniform binary target observed through a finite symmetric experiment, replacing the classification-error constraint with its necessary mutual-information threshold strictly lowers the infimum of entropy production under a common operation time, integrated mobility budget, and sufficiently large finite transition-rate cap. The separation holds whenever the target error lies strictly between the Bayes error of the observations and chance. Two results establish this physical gap. First, ordering observations by posterior confidence gives exact transport--risk and transport--information frontiers. Observations with the same Bayes error can have different cost frontiers. Second, we construct bounded-rate protocols that realize prescribed encoders with write probabilities below one, starting from exact reset, with an explicit excess cost above the transport bound. An achievable information-constrained cost then falls below a lower bound valid for every task-feasible protocol. Examples with repeated noisy observations illustrate the separation. The results identify a limitation of information-only benchmarks for physical classification: task accuracy and kinetic constraints must be retained explicitly. The cost analyzed is total entropy production during memory writing, excluding data acquisition, controller operation, and subsequent reset. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-10-02 in math.IT). Categorie arXiv: Information Theory (cs.IT). Pagina del lavoro: https://arxiv.org/abs/2610.00291 — 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 2026-10-06T16:13:30.410Z dalla pagina https://arxiv.org/catchup/math.IT/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).