AI summaryⓘ
The authors study how controllers with limited resources can make it impossible to set prices exactly at a target value because their constraints exclude the target price from possible options. They explain this problem using a technical concept called support-exclusion and propose a new pricing method that tracks feasible price ranges and adjusts for bias in estimation. Their approach uses a special timing tool, the realized information clock, to create confidence intervals that reflect the real learning progress. Experiments confirm that their method correctly identifies when precise pricing is doable and wisely avoids making strong guesses when resources limit feasible pricing. Overall, the authors highlight that simply exploring cheaper options is not always enough to learn target prices precisely under resource limits.
resource-constrained pricingfixed-price inferencesupport-exclusionlocal non-identificationrealized information clocktarget-aware controllerstudentized intervalsregret-information tradeoffcalibrationdiagnostic abstention
Authors
Ruicheng Ao, Jiashuo Jiang, David Simchi-Levi
Abstract
Resource-constrained pricing controllers can make fixed-price inference impossible: the controller's resource state may remove the target price neighborhood from the feasible set, even when every realized action has a known positive density. We formalize this support-exclusion failure through a local non-identification result and a realized information clock. We then design a target-aware pricing controller that certifies feasible target bands and logs continuous local densities. Localized debiasing gives studentized intervals whose width is governed by this clock. The resulting regret--information accounting, stated up to pilot re-solving error, shows that cheap exploration can be insufficient for inference: polynomial target mass gives polynomial rates, while a pure $1/t$ target branch does not yield shrinking fixed-target intervals without additional local movement. Experiments show calibration in certified bands and diagnostic abstention when the resource state collapses target support.