English

Universally consistent predictive distributions

Machine Learning 2017-08-31 v2

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.

Cite

@article{arxiv.1708.01902,
  title  = {Universally consistent predictive distributions},
  author = {Vladimir Vovk},
  journal= {arXiv preprint arXiv:1708.01902},
  year   = {2017}
}

Comments

26 pages

R2 v1 2026-06-22T21:07:59.995Z