Calibrated Forecasts: The Minimax Proof
arXiv:2209.05863v230 citationsh-index: 44
Originality Synthesis-oriented
AI Analysis
This addresses the theoretical foundation for calibrated forecasts in prediction and game theory, but it is incremental as it formalizes an existing proof from 1995.
The paper tackles the problem of proving the existence of calibrated forecasts by providing a formal proof using the minimax theorem, showing that N^3 periods suffice to achieve a calibration error of at most 1/N.
A formal write-up of the simple proof (1995) of the existence of calibrated forecasts by the minimax theorem, which moreover shows that $N^3$ periods suffice to guarantee a calibration error of at most $1/N$.