...
首页> 外文期刊>Information Theory, IEEE Transactions on >Computation of Universal Objects for Distributions Over Co-Trees
【24h】

Computation of Universal Objects for Distributions Over Co-Trees

机译:协同树上分布的通用对象的计算

获取原文
获取原文并翻译 | 示例
           

摘要

For an ordered set, consider the model of distributions $P$ for which an element that precedes another element is considered the more significant one in the sense that the implication $aleq bRightarrow P(a)geq P(b)$ holds. It will be shown that if the ordered set is a finite co-tree, then the universal predictor for the model or, equivalently, the corresponding universal code, can be determined exactly via an algorithm of low complexity. Natural relations to problems on the computation of capacity and on the determination of information projections are established. More surprisingly, a direct connection to a problem of isotone regression also appears possible.
机译:对于有序集,请考虑分布模型$ P $,对于该模型,在含义$ aleq bRightarrow P(a)geq P(b)$成立的意义上,另一个元素之前的元素被认为是更重要的分布。将显示出,如果有序集合是有限的协树,则可以通过低复杂度的算法精确地确定模型的通用预测器或等效地相应的通用代码。建立了与能力计算和信息预测确定问题的自然关系。更令人惊讶的是,与同质异构回归问题的直接联系也似乎是可能的。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号