Efficient Competitions and Online Learning with Strategic Forecasters

02/16/2021
by   Rafael Frongillo, et al.
0

Winner-take-all competitions in forecasting and machine-learning suffer from distorted incentives. Witkowskiet al. 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(nlog 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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

04/20/2018

Online Improper Learning with an Approximation Oracle

We revisit the question of reducing online learning to approximate optim...
03/16/2017

Efficient Online Learning for Optimizing Value of Information: Theory and Application to Interactive Troubleshooting

We consider the optimal value of information (VoI) problem, where the go...
10/14/2020

Online Learning with Vector Costs and Bandits with Knapsacks

We introduce online learning with vector costs () where in each time ste...
02/20/2020

No-Regret and Incentive-Compatible Online Learning

We study online learning settings in which experts act strategically to ...
08/09/2014

Normalized Online Learning

We introduce online learning algorithms which are independent of feature...
09/07/2018

When Hashing Met Matching: Efficient Search for Potential Matches in Ride Sharing

We study the problem of matching rides in a ride sharing platform. Such ...
01/21/2020

TopRank+: A Refinement of TopRank Algorithm

Online learning to rank is a core problem in machine learning. In Lattim...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.