Universally consistent predictive distributions
Abstract
This paper describes simple universally consistent procedures of probability forecasting that satisfy a natural property of small-sample validity, under the assumption that the observations are produced independently in the IID fashion.
- Publication:
-
arXiv e-prints
- Pub Date:
- August 2017
- arXiv:
- arXiv:1708.01902
- Bibcode:
- 2017arXiv170801902V
- Keywords:
-
- Computer Science - Machine Learning;
- 68Q32;
- 62G20 (Primary) 68M20;
- 68T05 (Secondary)
- E-Print:
- 26 pages