Efficient Competitions and Online Learning with Strategic Forecasters

Abstract

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.

This paper will be presented at The Twenty-Second ACM Conference on Economics and Computation (EC '21), July 18-23, 2021, Budapest, Hungary