arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1610.08239cs.LGmath.STstat.MLstat.TH
收藏

贝叶斯做不到的事

Things Bayes can't do

INRIA(法国国家信息与自动化研究所)

Daniil Ryabko

摘要:

在一般的概率环境中考虑了给定过去的下一个事件的条件概率的预测问题。给定一个任意的(大的,不可数的)预测器集合C,我们想构造一个单一的预测器,它在任何数据上的表现都是渐近的,并且是C中的最佳预测器。在这里,我们证明了存在这样的预测器存在的集合C,但它们都不是先验集中在C上的贝叶斯预测器。换句话说,存在一个具有次线性后悔的预测器,但每个贝叶斯预测器都必须具有线性后悔。这一负面发现与以前的结果形成鲜明对比,以前的结果建立了相反的情况下,当$C$中的一个预测实现渐近消失的错误。在这种情况下,如果有一个预测器,实现渐近消失的误差为任何措施在C中,那么有一个贝叶斯预测器,也有这个属性,其先验集中在(可数子集)C。

英文摘要:

The problem of forecasting conditional probabilities of the next event given the past is considered in a general probabilistic setting. Given an arbitrary (large, uncountable) set C of predictors, we would like to construct a single predictor that performs asymptotically as well as the best predictor in C, on any data. Here we show that there are sets C for which such predictors exist, but none of them is a Bayesian predictor with a prior concentrated on C. In other words, there is a predictor with sublinear regret, but every Bayesian predictor must have a linear regret. This negative finding is in sharp contrast with previous results that establish the opposite for the case when one of the predictors in $C$ achieves asymptotically vanishing error. In such a case, if there is a predictor that achieves asymptotically vanishing error for any measure in C, then there is a Bayesian predictor that also has this property, and whose prior is concentrated on (a countable subset of) C.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑