Skip to content
conftrace_
2011 COLT COLT 2011

Does an Efficient Calibrated Forecasting Strategy Exist?

Abstract

We recall two previously-proposed notions of asymptotic calibration for a forecaster making a sequence of probability predictions. We note that the existence of efficient algorithms for calibrated forecasting holds only in the case of binary outcomes. We pose the question: do there exist such efficient algorithms for the general (non-binary) case?

❓ The Questioner
🚀 Conference Pioneer - COLT 2011
🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization
📈 Trend Setter - Reasoning
🧭 Keyword Pioneer - probability calibration
🐣 Hot Topic Early Bird - game theory

Authors

Jacob Abernethy, Shie Mannor

Topics

Artificial Intelligence > Core AI > Game AI Machine Learning > Optimization & Theory > Optimization Machine Learning > Optimization & Theory > Theory Machine Learning > Learning Types > Online Learning Artificial Intelligence > Core AI > Reasoning Mathematics & Optimization > Optimization > Game Theory Mathematics & Optimization > Probability > Stochastic Processes

Keywords

online learning game theory probability calibration sequential prediction probability prediction calibrated forecasting asymptotic calibration binary outcome
Download PDF

More from COLT 2011

All COLT 2011 papers →
Agnostic KWIK learning and efficient approximate reinforcement learning
The Sample Complexity of Dictionary Learning
Identifiability of Priors from Bounded Sample Sizes with Applications to Transfer Learning
Bounds on Individual Risk for Log-loss Predictors
A simple multi-armed bandit algorithm with optimal variation-bounded regret
Minimax Algorithm for Learning Rotations