Citation:
Dean P. Foster, S. H. . (2015). Smooth Calibration, Leaky Forecasts, and Finite Recall. Discussion Papers. presented at the 9. Retrieved from http://www.ma.huji.ac.il/hart/abs/calib-eq.html
Abstract:
We propose to smooth out the calibration score, which measures how good a forecaster is, by combining nearby forecasts. While regular calibration can be guaranteed only by randomized forecasting procedures, we show that smooth calibration can be guaranteed by deterministic procedures. As a consequence, it does not matter if the forecasts are leaked, i.e., made known in advance: smooth calibration can nevertheless be guaranteed (while regular calibration cannot). Moreover, our procedure has finite recall, is stationary, and all forecasts lie on a finite grid. We also consider related problems: online linear regression, weak calibration, and uncoupled Nash dynamics in n-person games.