Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Learning in Presence of Strategic Behavior

Efficient Competitions and Online Learning with Strategic Forecasters

Anish Thilagar · Rafael Frongillo · Bo Waggoner · Robert Gomez


Abstract: Winner-take-all competitions in forecasting and machine-learning suffer from distorted incentives.Witkowski et al. identified this problem and proposed ELF, a truthful mechanism to select a winner.We show that, from a pool of nn forecasters, ELF requires Θ(nlogn)Θ(nlogn) events or test data points to select a near-optimal forecaster with high probability.We then show that standard online learning algorithms select an ϵϵ-optimal forecaster using only O(log(n)/ϵ2)O(log(n)/ϵ2) 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.

Chat is not available.