连续与随机防御性预测：统一视角
机器学习
2007-08-23 v2
摘要
防御性预测是一种将概率定律（以博弈论术语表述为怀疑者的策略）转化为预测算法的方法。已知有两种防御性预测变体：“连续”变体，其中假设怀疑者的移动以（半）连续的方式依赖于预测，并产生确定性预测；以及“随机”变体，其中怀疑者的移动对预测的依赖是任意的，且预测者的移动允许是随机的。本说明表明，随机变体可以通过将怀疑者的移动模糊化以使其连续化，从而从连续变体中获得。
引用
@article{arxiv.0708.2353,
title = {Continuous and randomized defensive forecasting: unified view},
author = {Vladimir Vovk},
journal= {arXiv preprint arXiv:0708.2353},
year = {2007}
}
评论
10 pages. The new version: (1) relaxes the assumption that the outcome space is finite, and now it is only assumed to be compact; (2) shows that in the case where the outcome space is finite of cardinality C, the randomized forecasts can be chosen concentrated on a finite set of cardinality at most C