No-Regret and Incentive-Compatible Online Learning
This addresses the challenge of strategic manipulation in online prediction for applications like forecasting, though it is incremental by building on existing wagering mechanisms.
The paper tackles the problem of designing online learning algorithms that are both no-regret with respect to the best fixed expert and incentive-compatible, ensuring experts report true beliefs, with experiments showing regret comparable to classic non-incentive-compatible algorithms on FiveThirtyEight datasets.
We study online learning settings in which experts act strategically to maximize their influence on the learning algorithm's predictions by potentially misreporting their beliefs about a sequence of binary events. Our goal is twofold. First, we want the learning algorithm to be no-regret with respect to the best fixed expert in hindsight. Second, we want incentive compatibility, a guarantee that each expert's best strategy is to report his true beliefs about the realization of each event. To achieve this goal, we build on the literature on wagering mechanisms, a type of multi-agent scoring rule. We provide algorithms that achieve no regret and incentive compatibility for myopic experts for both the full and partial information settings. In experiments on datasets from FiveThirtyEight, our algorithms have regret comparable to classic no-regret algorithms, which are not incentive-compatible. Finally, we identify an incentive-compatible algorithm for forward-looking strategic agents that exhibits diminishing regret in practice.