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.

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?

Cite this Paper


BibTeX
@InProceedings{pmlr-v19-abernethy11a, title = {Does an Efficient Calibrated Forecasting Strategy Exist?}, author = {Abernethy, Jacob and Mannor, Shie}, booktitle = {Proceedings of the 24th Annual Conference on Learning Theory}, pages = {809--812}, year = {2011}, editor = {Kakade, Sham M. and von Luxburg, Ulrike}, volume = {19}, series = {Proceedings of Machine Learning Research}, address = {Budapest, Hungary}, month = {09--11 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v19/abernethy11a/abernethy11a.pdf}, url = {https://proceedings.mlr.press/v19/abernethy11a.html}, 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?} }
Endnote
%0 Conference Paper %T Does an Efficient Calibrated Forecasting Strategy Exist? %A Jacob Abernethy %A Shie Mannor %B Proceedings of the 24th Annual Conference on Learning Theory %C Proceedings of Machine Learning Research %D 2011 %E Sham M. Kakade %E Ulrike von Luxburg %F pmlr-v19-abernethy11a %I PMLR %P 809--812 %U https://proceedings.mlr.press/v19/abernethy11a.html %V 19 %X 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?
RIS
TY - CPAPER TI - Does an Efficient Calibrated Forecasting Strategy Exist? AU - Jacob Abernethy AU - Shie Mannor BT - Proceedings of the 24th Annual Conference on Learning Theory DA - 2011/12/21 ED - Sham M. Kakade ED - Ulrike von Luxburg ID - pmlr-v19-abernethy11a PB - PMLR DP - Proceedings of Machine Learning Research VL - 19 SP - 809 EP - 812 L1 - http://proceedings.mlr.press/v19/abernethy11a/abernethy11a.pdf UR - https://proceedings.mlr.press/v19/abernethy11a.html AB - 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? ER -
APA
Abernethy, J. & Mannor, S.. (2011). Does an Efficient Calibrated Forecasting Strategy Exist?. Proceedings of the 24th Annual Conference on Learning Theory, in Proceedings of Machine Learning Research 19:809-812 Available from https://proceedings.mlr.press/v19/abernethy11a.html.

Related Material