No-Regret Learning in Bilateral Trade via Global Budget Balance

TL;DR

This paper develops no-regret algorithms for online bilateral trade with a relaxed global budget balance constraint, achieving near-optimal regret bounds under various feedback models.

Contribution

It introduces the concept of global budget balance for online bilateral trade and provides the first no-regret algorithms under this relaxation with different feedback settings.

Findings

Achieves  O(\u221A T) regret in full-feedback model.

Provides  O(T^{3/4}) regret with one-bit feedback.

Establishes a   T^{5/7} lower bound for limited feedback.

Abstract

Bilateral trade models the problem of intermediating between two rational agents -- a seller and a buyer -- both characterized by a private valuation for an item they want to trade. We study the online learning version of the problem, in which at each time step a new seller and buyer arrive and the learner has to set prices for them without any knowledge about their (adversarially generated) valuations. In this setting, known impossibility results rule out the existence of no-regret algorithms when budget balanced has to be enforced at each time step. In this paper, we introduce the notion of \emph{global budget balance}, which only requires the learner to fulfill budget balance over the entire time horizon. Under this natural relaxation, we provide the first no-regret algorithms for adversarial bilateral trade under various feedback models. First, we show that in the full-feedback model, the learner can guarantee $\tilde O(\sqrt{T})$ regret against the best fixed prices in hindsight, and that this bound is optimal up to poly-logarithmic terms. Second, we provide a learning algorithm guaranteeing a $\tilde O(T^{3/4})$ regret upper bound with one-bit feedback, which we complement with a $\Omega(T^{5/7})$ lower bound that holds even in the two-bit feedback model. Finally, we introduce and analyze an alternative benchmark that is provably stronger than the best fixed prices in hindsight and is inspired by the literature on bandits with knapsacks.