跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2606.03736 · v4

Adaptive Inference for Resource-Constrained Dynamic Pricing

首次提交 2026-06-02 22:52
版本更新 2026-11-19 09:11
雷达观测 2026-11-20 10:50
arXiv ↗PDF ↗

摘要

We study dynamic pricing over a finite selling horizon when limited resource capacity determines revenue and the observations available for inference at a prespecified price. Resource depletion can remove the target neighborhood from the feasible price set, changing the experiment generated by the pricing policy. We develop inference-aware re-solving controllers that check target-band feasibility before current covariates arrive and log the pricing mixture. Target-reserved and smooth controllers take population mean-pair geometry as a predeployment input; learned barycentric re-solving instead estimates stationary mean-consumption vectors of predeclared component kernels. On an affine binding-capacity family, an exact-input target-reserved controller assigning mass t−γt^{-γ} obtains an information clock of order T1−γT^{1-γ} in probability, radius Op{T−(1−γ)/2}O_p\{T^{-(1-γ)/2}\}, and, under an exposed-face reward identity, a signed fluid-benchmark gap bounded above by O(log⁡T+T1−γ)O(\log T+T^{1-γ}). Under the exogenous affine-face condition, predeclared target support, and polynomial error spending with exponent greater than one, learned barycentric re-solving has a linear information clock in probability and an O(log⁡T)O(\log T) signed-gap upper bound; centered local pricing has the same orders under slack capacity and global target optimality. An exact-input, target-compatible smooth alternative without reservation gives a linear clock in probability, an Op(T−1/2)O_p(T^{-1/2}) deterministic-envelope radius with unconditional coverage and reporting probability tending to one, and an O(log⁡2T)O(\log^2 T) signed-gap upper bound. Boundary results show when physical support is lost and why a 1/t1/t target branch yields only Op(1)O_p(1) information if it is the sole target-local source. The policy reports an interval when its prespecified support and information conditions hold and otherwise abstains.

作者备注:There is some presentation issue I need to revise significantly

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v4,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v4 · 2026-11-19 09:11 · 最新观测版本

Adaptive Inference for Resource-Constrained Dynamic Pricing

We study dynamic pricing over a finite selling horizon when limited resource capacity determines revenue and the observations available for inference at a prespecified price. Resource depletion can remove the target neighborhood from the feasible price set, changing the experiment generated by the pricing policy. We develop inference-aware re-solving controllers that check target-band feasibility before current covariates arrive and log the pricing mixture. Target-reserved and smooth controllers take population mean-pair geometry as a predeployment input; learned barycentric re-solving instead estimates stationary mean-consumption vectors of predeclared component kernels. On an affine binding-capacity family, an exact-input target-reserved controller assigning mass t−γt^{-γ} obtains an information clock of order T1−γT^{1-γ} in probability, radius Op{T−(1−γ)/2}O_p\{T^{-(1-γ)/2}\}, and, under an exposed-face reward identity, a signed fluid-benchmark gap bounded above by O(log⁡T+T1−γ)O(\log T+T^{1-γ}). Under the exogenous affine-face condition, predeclared target support, and polynomial error spending with exponent greater than one, learned barycentric re-solving has a linear information clock in probability and an O(log⁡T)O(\log T) signed-gap upper bound; centered local pricing has the same orders under slack capacity and global target optimality. An exact-input, target-compatible smooth alternative without reservation gives a linear clock in probability, an Op(T−1/2)O_p(T^{-1/2}) deterministic-envelope radius with unconditional coverage and reporting probability tending to one, and an O(log⁡2T)O(\log^2 T) signed-gap upper bound. Boundary results show when physical support is lost and why a 1/t1/t target branch yields only Op(1)O_p(1) information if it is the sole target-local source. The policy reports an interval when its prespecified support and information conditions hold and otherwise abstains.

查看此版本解读 →查看此版本原文 ↗