Learning Anonymous Pricing for Online Resource Allocation

2026-06-25

AI Summary

This work addresses the fairness concerns in online resource allocation arising from dynamic pricing and its dependence on user arrival order. The authors propose a sample- and query-efficient learning mechanism for anonymous pricing that integrates a dual pricing framework with randomized anonymous price vectors. Under the assumption that users arrive in an unknown order drawn independently from identical distributions, they establish—for the first time—that an approximately optimal anonymous pricing policy can be learned using only a polynomial number of samples or value queries. The proposed mechanism simultaneously optimizes social welfare and ensures fairness, substantially reducing reliance on prior distributional knowledge and offering both theoretical guarantees and a practical solution for efficient and equitable online resource allocation.

Abstract

We study the online resource allocation problem, where a seller sequentially receives independent requests for $m$ types of resources with limited supplies from $n$ heterogeneous agents arriving in an unknown order. Each request from an agent can be fulfilled in different ways, with resource consumption in $[0,1]^m$, and generates different values for the agent. The objective of the seller is to maximize the social welfare, which is the sum of the values obtained from each agent. Recently, Ghuge, Singla, and Wang [GSW STOC'25] studied the learnability of the online resource allocation problem with heterogeneous agents and proposed a learnable pricing algorithm using only a single sample. However, their core algorithm is a dynamic pricing algorithm, which may introduce fairness concerns, as different agents face different prices. Furthermore, the algorithm crucially needs to know the arrival order of the agents in advance. To address these issues, in this paper, we study the learnability of anonymous pricing algorithms for online resource allocation using samples and queries to agents' value distributions. First, we show that a polynomial number of samples suffices to learn the classic dual pricing algorithm. Second, we show that a polynomial number of pricing queries suffices to learn a near-optimal anonymous pricing algorithm, in which the item pricing vector faced by each agent is drawn from the same predetermined distribution.

Problem

• online resource allocation
• anonymous pricing
• social welfare
• heterogeneous agents
• learnability

Innovation

• anonymous pricing
• online resource allocation
• sample complexity
• pricing queries
• learnability