首页 | 本学科首页   官方微博 | 高级检索  
     


The weak aggregating algorithm and weak mixability
Authors:Yuri Kalnishkan  Michael V. Vyugin
Affiliation:Department of Computer Science and Computer Learning Research Centre, Royal Holloway, University of London, Egham, Surrey, TW20 0EX, United Kingdom
Abstract:This paper resolves the problem of predicting as well as the best expert up to an additive term of the order o(n), where n is the length of a sequence of letters from a finite alphabet. We call the games that permit this weakly mixable and give a geometrical characterisation of the class of weakly mixable games. Weak mixability turns out to be equivalent to convexity of the finite part of the set of superpredictions. For bounded games we introduce the Weak Aggregating Algorithm that allows us to obtain additive terms of the form View the MathML source.
Keywords:On-line learning   Predicting individual sequences   Prediction with expert advice   General loss functions
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号