Metraipolis › archive › dc_3905348fc17d
Simultaneous Gradient Learning in First-Price Auctions — arXiv:2610.38487
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38487
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:22:23.280Z
- SHA-256 of the archived text
37f6ab18c03cf4ae8e2219753577e81f4004187c5099d5d600d12b7952317e16- Stable URL of this page
https://metraipolis.com/documento/dc_3905348fc17d
How to cite
Simultaneous Gradient Learning in First-Price Auctions — arXiv:2610.38487 — arXiv (en), https://arxiv.org/abs/2610.38487 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3905348fc17d (Metraipolis archive dc_3905348fc17d, sha256 37f6ab18c03cf4ae8e2219753577e81f4004187c5099d5d600d12b7952317e16)
BibTeX
@misc{dc3905348fc17d,
title = {Simultaneous Gradient Learning in First-Price Auctions — arXiv:2610.38487},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38487},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3905348fc17d; sha256 37f6ab18c03cf4ae8e2219753577e81f4004187c5099d5d600d12b7952317e16},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38487. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study equilibrium learning in discretized Bayesian games, focusing on first-price auctions as a testbed for gradient-based learning dynamics under private information. While the symmetric independent private values model admits a unique Bayesian correlated equilibrium (BCE) in the continuous limit, standard convergence guarantees for gradient-based learners do not apply: classical no-regret theory predicts convergence only to Bayesian coarse correlated equilibria (BCCE), which can remain large and far from the competitive equilibrium even under fine discretizations. To bridge this gap, we introduce the notion of Bayesian semicoarse correlated equilibrium (BSCCE), an equilibrium concept that refines BCCE by restricting deviations to probability-preserving transformations consistent with projected gradient dynamics. We provide a linear programming characterization of BSCCE with polynomially many variables and constraints and establish the inclusion hierarchy $BCE \subseteq BSCCE \subseteq BCCE$. Our main finding is that the BSCCE set contracts in many cases as the discretization of the Bayesian game is refined. Even with priors for which BCCE fails to concentrate, the diameter of the BSCCE polytope shrinks toward zero, indicating convergence to the unique continuous-game Bayes-Nash equilibrium. These results provide a principled explanation for the observed robustness of gradient-based learning in discretized Bayesian games, showing that these dynamics select a smaller equilibrium set than standard no-regret theory predicts. Tema degli esploratori: economia dei servizi IA (elenco arXiv cs.GT, nuovi lavori del giorno). Categorie arXiv: Computer Science and Game Theory (cs.GT) ; Theoretical Economics (econ.TH). Pagina del lavoro: https://arxiv.org/abs/2610.38487 — 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 2026-10-31T06:08:53.362Z dalla pagina https://arxiv.org/list/cs.GT/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).