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 1111.3182cs.ITmath.IT
收藏

上下文树切换

Context Tree Switching

Joel Veness, Kee Siong Ng, Marcus Hutter, Michael Bowling

摘要:

本文介绍了上下文树切换技术,上下文树加权预测的二进制,平稳,n-Markov源的修改。通过修改上下文树加权的递归加权方案,可以在严格更大的模型类别上混合,而不会增加原始算法的渐近时间或空间复杂度。我们证明,这种泛化保留了理想的理论属性上下文树加权平稳的n-Markov源,并表明经验表明,这种新技术导致一致的改进上下文树加权卡尔加里语料库上测量。

英文摘要:

This paper describes the Context Tree Switching technique, a modification of Context Tree Weighting for the prediction of binary, stationary, n-Markov sources. By modifying Context Tree Weighting's recursive weighting scheme, it is possible to mix over a strictly larger class of models without increasing the asymptotic time or space complexity of the original algorithm. We prove that this generalization preserves the desirable theoretical properties of Context Tree Weighting on stationary n-Markov sources, and show empirically that this new technique leads to consistent improvements over Context Tree Weighting as measured on the Calgary Corpus.

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。

↑