Инд. авторы:	Ryabko D.
Заглавие:	Things Bayes can’t do
Библ. ссылка:	Ryabko D. Things Bayes can’t do // Lecture Notes in Computer Science. - 2016. - Vol.9925 LNAI. - P.253-260. - ISSN 0302-9743. - EISSN 1611-3349.
Внешние системы:	DOI: 10.1007/978-3-319-46379-7_17; SCOPUS: 2-s2.0-84994169040;
Реферат:	eng: 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. © Springer International Publishing Switzerland 2016.
Ключевые слова:	Artificial intelligence; Sublinear; Sharp contrast; nocv1; Countable subsets; Conditional probabilities; Bayesian; Computers; Computer science;
Издано:	2016
Физ. характеристика:	с.253-260
Конференция:	Название: 27th International Conference on Algorithmic Learning Theory Аббревиатура: ALT 2016 Даты проведения: 2016-10-19 - 2016-10-21