Metraipolis › archive › dc_2a3e8d85bb5b
The Cost of Conservation: Coordination-Memory Laws for Exact-Support Generation — arXiv:2609.26126
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26126
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:45:33.889Z
- SHA-256 of the archived text
10a31fa13b3a953cf72c6b67dca5d3431fb0c8750445eefeee64bc0f9c3aa0a8- Stable URL of this page
https://metraipolis.com/documento/dc_2a3e8d85bb5b
How to cite
The Cost of Conservation: Coordination-Memory Laws for Exact-Support Generation — arXiv:2609.26126 — arXiv (en), https://arxiv.org/abs/2609.26126 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a3e8d85bb5b (Metraipolis archive dc_2a3e8d85bb5b, sha256 10a31fa13b3a953cf72c6b67dca5d3431fb0c8750445eefeee64bc0f9c3aa0a8)
BibTeX
@misc{dc2a3e8d85bb5b,
title = {The Cost of Conservation: Coordination-Memory Laws for Exact-Support Generation — arXiv:2609.26126},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26126},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a3e8d85bb5b; sha256 10a31fa13b3a953cf72c6b67dca5d3431fb0c8750445eefeee64bc0f9c3aa0a8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26126. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many AI systems make decisions locally, even when every realized output must obey an additive conservation law, such as selecting exactly a fixed number of items. This constraint can be statistically invisible: small subsets of a balanced fixed-budget output look increasingly independent, yet communication-free coordinate-parallel generation needs exponentially many pre-shared plans, while a sequential exact sampler needs only logarithmic memory. We study product measures conditioned on additive conservation laws in the intermediate regime where one plan is selected before a fixed-order pass, every plan is a bounded-state stochastic executor whose support is entirely legal, and the mixture of plan laws approximates the target distribution in total variation. Our main result identifies the optimal asymptotic selector rate, up to constant factors, with the killed spectral profile of the conservation-difference walk. The resulting coordination cost decreases as an inverse power of live-state width, with an exponent determined by intrinsic conservation rank rather than alphabet size; the law extends to noncentral budgets and heterogeneous local scores. The converse is driven by a state-versus-resource-sum obstruction, while a rate-matching construction compiles discrepancy control into exact-support finite-state plans. Complementary results characterize block-parallel plan complexity and the benefit of programmable output order. Together, these results show precisely how online memory substitutes for front-loaded coordination in exact-support generation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computational Complexity (cs.CC). Pagina del lavoro: https://arxiv.org/abs/2609.26126 — 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 2026-10-08T13:18:38.148Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).