Learning optimal forecast aggregation in partial evidence environments

DOI10.1287/MOOR.2020.1080MaRDI QIDQ5000648zbMATH OpenOpenAlexFDO

Authors Yakov Babichenko, Dan Garber

Publication date 15 July 2021

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1802.07107

zbMATH Keywords

online learninginformation aggregationBayesian experts

Mathematics Subject Classification ID

Rationality and learning in game theory (91A26) Mechanism design theory (91B03)

Abstract: We consider the forecast aggregation problem in repeated settings, where the forecasts are done on a binary event. At each period multiple experts provide forecasts about an event. The goal of the aggregator is to aggregate those forecasts into a subjective accurate forecast. We assume that experts are Bayesian; namely they share a common prior, each expert is exposed to some evidence, and each expert applies Bayes rule to deduce his forecast. The aggregator is ignorant with respect to the information structure (i.e., distribution over evidence) according to which experts make their prediction. The aggregator observes the experts' forecasts only. At the end of each period the actual state is realized. We focus on the question whether the aggregator can learn to aggregate optimally the forecasts of the experts, where the optimal aggregation is the Bayesian aggregation that takes into account all the information (evidence) in the system. We consider the class of partial evidence information structures, where each expert is exposed to a different subset of conditionally independent signals. Our main results are positive; We show that optimal aggregation can be learned in polynomial time in a quite wide range of instances of the partial evidence environments. We provide a tight characterization of the instances where learning is possible and impossible.

Recommendations

• Bayesian aggregation of two forecasts in the partial information framework
• Optimal probability aggregation based on generalized Brier scoring
• A maximum likelihood approach to combining forecasts
• Maximum Entropy Aggregation of Expert Predictions
• Publication:3484159

Cites work

• A Multiplicative Formula for Aggregating Probability Assessments
• Bayesian aggregation of two forecasts in the partial information framework
• Budget feasible mechanism design, from prior-free to Bayesian
• Combining Probability Forecasts
• Identifiable information structures
• Optimal Linear Opinion Pools
• Prediction, Learning, and Games
• Repeated games with incomplete information. With the collaboration of Richard E. Stearns
• Robustness and separation in multidimensional screening
• Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit
• Strictly Proper Scoring Rules, Prediction, and Estimation
• The Opinion Pool
• The nu expression for probabilistic data integration
• The weighted majority algorithm

Cited in

(3)

• Optimal probability aggregation based on generalized Brier scoring
• From Proper Scoring Rules to Max-Min Optimal Forecast Aggregation
• Bayesian aggregation of two forecasts in the partial information framework

This page was built for publication: Learning optimal forecast aggregation in partial evidence environments

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5000648)