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 $\Theta(n\log n)$ events or test data points to select a near-optimal forecaster with high probability. We then show that standard online learning algorithms select an $\epsilon$-optimal forecaster using only $O(\log(n) / \epsilon^2)$ 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.
翻译:预测和机器学习方面的赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-赢家-竞争受到扭曲的激励。Witkows等人2018年发现,标准在线学习算法选择一个只使用$O(log(n)/\epsilon2)/ 最优的预测者-最佳预测者-最佳预测者-最佳预测者-最佳预测者-只使用高额-以强烈的近似真真真真真真真真真真真假保证方式选择胜者-保证。我们然后运用这些机制来为非战略专家获得第一个无假战略专家的无真真假战略专家的保证。我们再应用这些机制是为了获得第一个无保证。