Metraipolis › archive › dc_9675c1a007bb
Learning to Design Information — arXiv:2611.05701
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05701
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:39:32.660Z
- SHA-256 of the archived text
079a93dcebb3a5accdd63aa22897f9d492a7ed309f1389843a7c630e9360d94d- Stable URL of this page
https://metraipolis.com/documento/dc_9675c1a007bb
How to cite
Learning to Design Information — arXiv:2611.05701 — arXiv (en), https://arxiv.org/abs/2611.05701 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9675c1a007bb (Metraipolis archive dc_9675c1a007bb, sha256 079a93dcebb3a5accdd63aa22897f9d492a7ed309f1389843a7c630e9360d94d)
BibTeX
@misc{dc9675c1a007bb,
title = {Learning to Design Information — arXiv:2611.05701},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05701},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9675c1a007bb; sha256 079a93dcebb3a5accdd63aa22897f9d492a7ed309f1389843a7c630e9360d94d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05701. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Information designers, such as large language models and online platforms, often do not know the subjective beliefs of their receivers or users. We construct learning algorithms enabling the designer to learn the belief of a strategic receiver through repeated interactions. Our learning algorithms are robust to the receiver's strategic manipulation of the learning process of the designer. We study regret relative to two benchmarks to measure the performance of the algorithms. The static benchmark is $T$ times the single-period optimum for the designer under a known belief. The dynamic benchmark, which is stronger, characterizes global dynamic optimality for the designer under a known belief. Our learning algorithms allow the designer to achieve no regret against both benchmarks at fast convergence speeds of $O(\frac{\log^2 T}{T})$, significantly faster than other approaches in the literature.
Tema degli esploratori: economia dei servizi IA (elenco arXiv econ.TH, nuovi lavori del giorno).
Categorie arXiv: Theoretical Economics (econ.TH).
Pagina del lavoro: https://arxiv.org/abs/2611.05701 — 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 2026-11-05T18:31:31.579Z dalla pagina https://arxiv.org/list/econ.TH/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).