Metraipolis › archive › dc_1971512cea7c

Optimal Contextual Pricing in Non-Stationary Environments — arXiv:2610.39803

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39803
License (as archived)
CC0-1.0
Archived
2026-11-01T02:25:15.515Z
SHA-256 of the archived text
9ec91d30e2dc9333be93305ed28f065eb5edf3b8c579b7c8d5a933dd48e5af0c
Stable URL of this page
https://metraipolis.com/documento/dc_1971512cea7c

How to cite

Optimal Contextual Pricing in Non-Stationary Environments — arXiv:2610.39803 — arXiv (en), https://arxiv.org/abs/2610.39803 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1971512cea7c (Metraipolis archive dc_1971512cea7c, sha256 9ec91d30e2dc9333be93305ed28f065eb5edf3b8c579b7c8d5a933dd48e5af0c)
BibTeX
@misc{dc1971512cea7c,
  title = {Optimal Contextual Pricing in Non-Stationary Environments — arXiv:2610.39803},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39803},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1971512cea7c; sha256 9ec91d30e2dc9333be93305ed28f065eb5edf3b8c579b7c8d5a933dd48e5af0c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39803. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study contextual dynamic pricing in a non-stationary environment. In each round, a seller observes a buyer's context, posts a price, and receives only binary purchase feedback. The buyer's value is linear in the context and an unobserved feature vector that may change over time, subject to a known total variation budget $V$. We measure dynamic regret against the first-best benchmark that extracts each buyer's full value. For identical contexts, we develop a deterministic algorithm that combines binary-search exploration, lower-envelope pricing, and periodic and inconsistency-triggered restarts. It achieves regret $O((\sqrt{TV}+1)\log T)$. With heterogeneous contexts, a new geometric difficulty arises: small feature changes can leave a relaxed feasible set narrow but far from the current feature vector. We address this difficulty through a multiscale shallow-pricing algorithm that maintains relaxed feasible sets and enclosing ellipsoids at several variation scales. Larger scales provide reliable localization certificates, while the smallest active scale determines the exploitation price. The algorithm achieves dynamic regret $O((d^2+d^{3/2}\sqrt{TV})\log^2 T)$, where $d$ is the context dimension. For fixed $d$, both guarantees match the lower bound $\Omega(\sqrt{TV}+\log\log T)$ up to logarithmic factors in $T$, establishing near-optimality among deterministic algorithms for every $V\in[0,T]$, including the stationary case.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.39803 — 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 2026-11-01T02:12:44.188Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).