Agnostic Insurability of Model Classes

Abstract

Motivated by problems in insurance, our task is to predict finite upper bounds on a future draw from an unknown distribution $p$ over natural numbers. We can only use past observations generated independently and identically distributed according to $p$. While $p$ is unknown, it is known to belong to a given collection $\mathcal{P}$ of probability distributions on the natural numbers.

Cite

Text

Santhanam and Anantharam. "Agnostic Insurability of Model Classes." Journal of Machine Learning Research, 2015.

Markdown

[Santhanam and Anantharam. "Agnostic Insurability of Model Classes." Journal of Machine Learning Research, 2015.](https://mlanthology.org/jmlr/2015/santhanam2015jmlr-agnostic/)

BibTeX

@article{santhanam2015jmlr-agnostic,
  title     = {{Agnostic Insurability of Model Classes}},
  author    = {Santhanam, Narayana and Anantharam, Venkat},
  journal   = {Journal of Machine Learning Research},
  year      = {2015},
  pages     = {2329-2355},
  volume    = {16},
  url       = {https://mlanthology.org/jmlr/2015/santhanam2015jmlr-agnostic/}
}