Does an Efficient Calibrated Forecasting Strategy Exist?


Jacob Abernethy, Shie Mannor ;
Proceedings of the 24th Annual Conference on Learning Theory, PMLR 19:809-812, 2011.


We recall two previously-proposed notions of \emphasymptotic 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?

Related Material