论文标题
提高了近似值的近似值
Improved Approximation to First-Best Gains-from-Trade
论文作者
论文摘要
我们研究了两项工具双边贸易。理想情况下，每当买方对商品的价值超过卖方的成本时，交易都应发生。但是，迈尔森（Myerson）和萨特维特（Satterthwaite）的经典结果表明，没有违反贝叶斯激励兼容性之一，个人合理性和弱平衡预算条件的情况下，没有任何机制能够实现这一目标。这激发了根据预期的从贸易中的预期增益来近似交易时近似交易的研究。最近，Deng，Mao，Sivan和Wang表明，随机使用者机制至少达到1/8.23的近似值。在本文中，我们将其提高到1/3.15。我们还确定卖方定价机制的确切最差案例近似值，假设买方的价值分布满足单调危害率属性。
We study the two-agent single-item bilateral trade. Ideally, the trade should happen whenever the buyer's value for the item exceeds the seller's cost. However, the classical result of Myerson and Satterthwaite showed that no mechanism can achieve this without violating one of the Bayesian incentive compatibility, individual rationality and weakly balanced budget conditions. This motivates the study of approximating the trade-whenever-socially-beneficial mechanism, in terms of the expected gains-from-trade. Recently, Deng, Mao, Sivan, and Wang showed that the random-offerer mechanism achieves at least a 1/8.23 approximation. We improve this lower bound to 1/3.15 in this paper. We also determine the exact worst-case approximation ratio of the seller-pricing mechanism assuming the distribution of the buyer's value satisfies the monotone hazard rate property.
