On Calibration Error of Randomized Forecasting Algorithms

9 years 7 days ago
On Calibration Error of Randomized Forecasting Algorithms
It has been recently shown that calibration with an error less than ∆ > 0 is almost surely guaranteed with a randomized forecasting algorithm, where forecasts are obtained by random rounding the deterministic forecasts up to ∆. We show that this error cannot be improved for a vast majority of sequences: we prove that, using a probabilistic algorithm, we can effectively generate with probability close to one a sequence “resistant” to any randomized rounding forecasting with an error much smaller than ∆. We also reformulate this result by means of a probabilistic game. Key words: Machine learning, Universal prediction, Randomized prediction, Algorithmic prediction, Calibration, Randomized rounding
Vladimir V. V'yugin
Added 14 Mar 2010
Updated 14 Mar 2010
Type Conference
Year 2007
Where ALT
Authors Vladimir V. V'yugin
Comments (0)