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 0903.4217cs.LGcs.AI
收藏

条件概率树估计分析及算法

Conditional Probability Tree Estimation Analysis and Algorithms

IBM Research(IBM研究院);Yahoo! Research(雅虎研究院)

Alina Beygelzimer, John Langford, Yuri Lifshits, Gregory Sorkin, Alex Strehl

摘要:

我们考虑的问题估计的条件概率的标签在时间$O(\log n)$,其中$n$是可能的标签的数量。我们分析了一个自然减少这个问题的一组二进制回归问题组织在一个树结构,证明了遗憾的范围,规模与深度的树。基于这种分析,我们提出了第一个在线算法,该算法可证明地在标签集上构建对数深度树来解决这个问题。我们测试的算法经验,表明它成功地工作在一个数据集与大致$10^6$标签。

英文摘要:

We consider the problem of estimating the conditional probability of a label in time $O(\log n)$, where $n$ is the number of possible labels. We analyze a natural reduction of this problem to a set of binary regression problems organized in a tree structure, proving a regret bound that scales with the depth of the tree. Motivated by this analysis, we propose the first online algorithm which provably constructs a logarithmic depth tree on the set of labels to solve this problem. We test the algorithm empirically, showing that it works succesfully on a dataset with roughly $10^6$ labels.

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。

↑