arXiv Open Access 2021

Efficient Competitions and Online Learning with Strategic Forecasters

Rafael Frongillo Robert Gomez Anish Thilagar Bo Waggoner
Lihat Sumber

Abstrak

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 $Θ(n\log n)$ events or test data points to select a near-optimal forecaster with high probability. We then show that standard online learning algorithms select an $ε$-optimal forecaster using only $O(\log(n) / ε^2)$ 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.

Topik & Kata Kunci

Penulis (4)

R

Rafael Frongillo

R

Robert Gomez

A

Anish Thilagar

B

Bo Waggoner

Format Sitasi

Frongillo, R., Gomez, R., Thilagar, A., Waggoner, B. (2021). Efficient Competitions and Online Learning with Strategic Forecasters. https://arxiv.org/abs/2102.08358

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓