有效的竞争和在线学习与战略预测
Efficient Competitions and Online Learning with Strategic Forecasters
摘要：
在预测和机器学习领域，赢者通吃的竞争受到了扭曲的激励。Witkowski等人在2018年发现了这个问题，并提出了ELF，这是一种选择获胜者的真实机制。我们发现，从一个池的$n$预测，ELF需要$Θ(n\log n)$事件或测试数据点，以选择一个接近最佳的预测与高概率。然后，我们表明，标准的在线学习算法选择一个$ε$ -最佳预测只使用$O(\log(n) / ε^2)$事件，通过一个强大的近似真实性保证。即使在非策略环境中，这个界限也是最佳的。然后，我们应用这些机制，为非短视的战略专家获得第一个不后悔的保证。
英文摘要：
Winner-take-all competitions in forecasting and machine-learning suffer from distorted incentives. Witkowski et al. 2018 identified this problem and proposed ELF, a truthful mechanism to select a winner. We show that, from a pool of $n$ forecasters, ELF requires $Θ(n\log n)$ events or test data points to select a near-optimal forecaster with high probability. We then show that standard online learning algorithms select an $ε$-optimal forecaster using only $O(\log(n) / ε^2)$ events, by way of a strong approximate-truthfulness guarantee. This bound matches the best possible even in the nonstrategic setting. We then apply these mechanisms to obtain the first no-regret guarantee for non-myopic strategic experts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
