Metraipolis › archive › dc_801ab1d2003c

Optimal Rates for Agentic Networked Information Aggregation — arXiv:2609.05318

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05318
License (as archived)
CC0-1.0
Archived
2026-10-16T22:45:45.147Z
SHA-256 of the archived text
db7dd5bdf14d3176445bddea5583caffdc7040c7e0f73c7dc789952e109bd845
Stable URL of this page
https://metraipolis.com/documento/dc_801ab1d2003c

How to cite

Optimal Rates for Agentic Networked Information Aggregation — arXiv:2609.05318 — arXiv (en), https://arxiv.org/abs/2609.05318 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_801ab1d2003c (Metraipolis archive dc_801ab1d2003c, sha256 db7dd5bdf14d3176445bddea5583caffdc7040c7e0f73c7dc789952e109bd845)
BibTeX
@misc{dc801ab1d2003c,
  title = {Optimal Rates for Agentic Networked Information Aggregation — arXiv:2609.05318},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05318},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_801ab1d2003c; sha256 db7dd5bdf14d3176445bddea5583caffdc7040c7e0f73c7dc789952e109bd845},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05318. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Building on the pioneering paper of Kearns, Roth, and Ryu (SODA'26), we study information aggregation in a networked learning model. The model captures a central pattern in agentic AI: each agent sees only part of the data and passes on only its own conclusion. Their model considers a linear regression problem with the mean squared error (MSE) loss. Agents sit in a DAG and each sees only a subset of the features and its parents' predictions, fits a linear predictor, and passes only its prediction forward. The benchmark is the full-feature learner that sees all raw features. A path of depth $D$ is $M$-covered if every block of $M$ consecutive agents collectively sees all raw features. Kearns, Roth, and Ryu proved that the excess mean squared error of the last agent on such a path is $O(M/\sqrt D)$, and gave a cyclic instance with excess error $\Omega(M/D)$ for $D<M^2$. We close this gap: the correct rate is constant up to depth $M^2$, and $\Theta(M^2/D)$ beyond it. We first give a sharper analysis of the cyclic instance and improve its lower bound to $\Omega(\sqrt{M/D})$ for $D<M^2$. We then construct, for every depth $D\ge M^2$, an $M$-covered path of depth $D$ with excess error $\Omega(M^2/D)$. The same instance gives the constant lower bound for all $D < M^2$. We also show that for any fixed distribution the excess error contracts geometrically along the path, ruling out any single instance that witnesses any polynomial lower bound at every depth. Finally, we prove the same optimal rate for logistic classification in the logit-passing model of Bateni et al., which considers the binary cross-entropy (BCE) loss. The same improved upper bound of $O(M^2/D)$ holds, and we transfer all the regression lower bounds by showing that on those examples the logistic path follows the least-squares path up to rescaling.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-09-07 in cs.GT).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Science and Game Theory (cs.GT); Theoretical Economics (econ.TH).
Pagina del lavoro: https://arxiv.org/abs/2609.05318 — 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 2026-10-16T22:29:53.700Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).