Metraipolis › archive › dc_2ace4c0b7dc2
Error Bounds for Statistical Estimators in BTL Model with Parametric Multivariate Utility Functions — arXiv:2609.26326
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26326
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T15:11:30.414Z
- SHA-256 of the archived text
a8021023814919e080ebe6975f56ee4cebc6403b675c8760c2f6f2ec9ae05289- Stable URL of this page
https://metraipolis.com/documento/dc_2ace4c0b7dc2
How to cite
Error Bounds for Statistical Estimators in BTL Model with Parametric Multivariate Utility Functions — arXiv:2609.26326 — arXiv (en), https://arxiv.org/abs/2609.26326 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ace4c0b7dc2 (Metraipolis archive dc_2ace4c0b7dc2, sha256 a8021023814919e080ebe6975f56ee4cebc6403b675c8760c2f6f2ec9ae05289)
BibTeX
@misc{dc2ace4c0b7dc2,
title = {Error Bounds for Statistical Estimators in BTL Model with Parametric Multivariate Utility Functions — arXiv:2609.26326},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26326},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ace4c0b7dc2; sha256 a8021023814919e080ebe6975f56ee4cebc6403b675c8760c2f6f2ec9ae05289},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26326. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study preference elicitation under the Bradley-Terry-Luce (BTL) model where the true partworth vector is unknown and has to be estimated as a parameter with elicited preference information. The set of selected pairwise queries is non-uniform, deterministic, and arbitrary over a collection of alternatives, provided that it satisfies a joint identifiability condition. We focus on understanding when the canonical maximum likelihood estimator (MLE) is finite and admits sharp error bounds without explicit compactness constraints on the feasible set or external regularizers. To this end, we derive minimax lower bounds under the standard bounded dynamic range condition, and find that the same Fisher-information geometry in the classic Cramér-Rao lower bounds underpins the finite-sample difficulty of the estimation problem. By combining a non-asymptotic expansion of the likelihood score equation with a fixed-point localization argument, we identify a design-dependent sample size threshold above which the unconstrained canonical MLE exists and is unique with high probability. The same expansion yields a decomposition of the estimation error into a linear stochastic term, an explicit second-order bias, and a higher-order remainder. A refined analysis gives sufficient sample size conditions under which the canonical MLE attains the minimax rates up to logarithmic and constant factors. These results provide a unified non-asymptotic theory for parametric utility elicitation and reveal when the inference is determined by response data alone rather than by external regularization. Preliminary numerical results are consistent with the theoretical findings. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.26326 — 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 2026-10-08T14:37:29.567Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).