Theory of recursive functions and effective computability
Theory of recursive functions and effective computability
Non-stochastic infinite and finite sequences
Theoretical Computer Science - Special issue Kolmogorov complexity
Calibration with many checking rules
Mathematics of Operations Research
On universal algorithms for adaptive forecasting
Problems of Information Transmission
| Hi-index | 0.00 |
The remarkable results of Foster and Vohra was a starting point for a series of papers which show that any sequence of outcomes can be learned (with no prior knowledge) using some universal randomized forecasting algorithm and forecast-dependent checking rules. We show that for the class of all computationally efficient outcome-forecast-based checking rules, this property is violated. Moreover, we present a probabilistic algorithm generating with probability close to one a sequence with a subsequence which simultaneously miscalibrates all partially weakly computable randomized forecasting algorithms. According to the Dawid's prequential framework we consider partial recursive randomized algorithms.