# No-Regret Online Prediction with Strategic Experts

arXiv: https://arxiv.org/abs/2305.15331 · HTML: https://mlsanity.com/paper/2305.15331/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 7 of 7)

- [Competitive caching with machine learned advice](https://mlsanity.com/paper/1802.05399/) (2018)
- [Fighting Bandits with a New Kind of Smoothness](https://mlsanity.com/paper/1512.04152/) (2015)
- [No-Regret and Incentive-Compatible Online Learning](https://mlsanity.com/paper/2002.08837/) (2020)
- [Guess Free Maximization of Submodular and Linear Sums](https://mlsanity.com/paper/1810.03813/) (2018)
- [Online Prediction with Selfish Experts](https://mlsanity.com/paper/1702.03615/) (2017)
- [Efficient Competitions and Online Learning with Strategic Forecasters](https://mlsanity.com/paper/2102.08358/) (2021)
- [ktexttt-experts -- Online Policies and Fundamental Limits](https://mlsanity.com/paper/2110.07881/) (2021)

## Abstract (arXiv)

We study a generalization of the online binary prediction with expert advice framework where at each round, the learner is allowed to pick m≥ 1 experts from a pool of K experts and the overall utility is a modular or submodular function of the chosen experts. We focus on the setting in which experts act strategically and aim to maximize their influence on the algorithm's predictions by potentially misreporting their beliefs about the events. Among others, this setting finds applications in forecasting competitions where the learner seeks not only to make predictions by aggregating different forecasters but also to rank them according to their relative performance. Our goal is to design algorithms that satisfy the following two requirements: 1) textitIncentive-compatible: Incentivize the experts to report their beliefs truthfully, and 2) textitNo-regret: Achieve sublinear regret with respect to the true beliefs of the best fixed set of m experts in hindsight. Prior works have studied this framework when m=1 and provided incentive-compatible no-regret algorithms for the problem. We first show that a simple reduction of our problem to the m=1 setting is neither efficient nor effective. Then, we provide algorithms that utilize the specific structure of the utility functions to achieve the two desired goals.