Forecasting Competitions with Correlated Events

03/24/2023
by   Rafael Frongillo, et al.
0

Beginning with Witkowski et al. [2022], recent work on forecasting competitions has addressed incentive problems with the common winner-take-all mechanism. Frongillo et al. [2021] propose a competition mechanism based on follow-the-regularized-leader (FTRL), an online learning framework. They show that their mechanism selects an ϵ-optimal forecaster with high probability using only O(log(n)/ϵ^2) events. These works, together with all prior work on this problem thus far, assume that events are independent. We initiate the study of forecasting competitions for correlated events. To quantify correlation, we introduce a notion of block correlation, which allows each event to be strongly correlated with up to b others. We show that under distributions with this correlation, the FTRL mechanism retains its ϵ-optimal guarantee using O(b^2 log(n)/ϵ^2) events. Our proof involves a novel concentration bound for correlated random variables which may be of broader interest.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/16/2021

Efficient Competitions and Online Learning with Strategic Forecasters

Winner-take-all competitions in forecasting and machine-learning suffer ...
research
01/05/2021

Incentive-Compatible Forecasting Competitions

We initiate the study of incentive-compatible forecasting competitions i...
research
12/07/2022

Modelling Correlated Bernoulli Data Part II: Inference

Binary data are highly common in many applications, however it is usuall...
research
12/05/2018

Optimal (and Benchmark-Optimal) Competition Complexity for Additive Buyers over Independent Items

The Competition Complexity of an auction setting refers to the number of...
research
08/20/2022

Near-Optimal Φ-Regret Learning in Extensive-Form Games

In this paper, we establish efficient and uncoupled learning dynamics so...
research
11/03/2019

A simple study of the correlation effects in the superposition of waves of electric fields: the emergence of extreme events

In this paper, we study the effects of correlated random phases in the i...
research
05/24/2023

Feature-aligned N-BEATS with Sinkhorn divergence

In this study, we propose Feature-aligned N-BEATS as a domain generaliza...

Please sign up or login with your details

Forgot password? Click here to reset