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 1607.02066math.PRmath.STstat.MLstat.TH
收藏

乘积型可交换特征概率函数的一个刻画

A characterization of product-form exchangeable feature probability functions

Marco Battiston, Stefano Favaro, Daniel M. Roy, Yee Whye Teh

摘要:

我们的特点是类的可交换的功能分配分配概率$V_{n,k}\prod_{l=1}^{k}W_{m_{l}}U_{n-m_{l}}$的$n$个人的功能分配,显示$k$功能与这些功能的计数$(m_{1},\ldots,m_{k})$。这个类的每个元素由一个可数矩阵$V$和两个非负权重序列$U$和$W$参数化。此外,施加一致性条件以保证当最后一个个体被整合出时,$n-1$个体的特征分配的分布从$n$个体的分布恢复。在定理1.1中,我们证明了满足相容性条件的这类模型的唯一成员是质量参数为$γ$的Indian Buffet过程的混合模型和维数参数为$N$的Beta-Bernoulli模型的混合模型。因此,我们提供了一个表征这两个模型作为唯一的,随机化的参数,一致的可交换的功能分配所需的产品形式。

英文摘要:

We characterize the class of exchangeable feature allocations assigning probability $V_{n,k}\prod_{l=1}^{k}W_{m_{l}}U_{n-m_{l}}$ to a feature allocation of $n$ individuals, displaying $k$ features with counts $(m_{1},\ldots,m_{k})$ for these features. Each element of this class is parametrized by a countable matrix $V$ and two sequences $U$ and $W$ of non-negative weights. Moreover, a consistency condition is imposed to guarantee that the distribution for feature allocations of $n-1$ individuals is recovered from that of $n$ individuals, when the last individual is integrated out. In Theorem 1.1, we prove that the only members of this class satisfying the consistency condition are mixtures of the Indian Buffet Process over its mass parameter $γ$ and mixtures of the Beta--Bernoulli model over its dimensionality parameter $N$. Hence, we provide a characterization of these two models as the only, up to randomization of the parameters, consistent exchangeable feature allocations having the required product form.

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。

↑