论文标题
混合模型中参数学习的代数和分析方法
Algebraic and Analytic Approaches for Parameter Learning in Mixture Models
论文作者
论文摘要
我们在一个维度的几个混合模型中提出了两种不同的参数学习方法。我们的第一种方法使用复杂的分析方法,适用于具有共同方差,具有共同成功概率的二项式混合物以及泊松混合物等的高斯混合物。一个示例结果是$ \ exp(o(n^{1/3}))$样本足以准确地学习$ k <n $ poisson发行的混合物,每个分布都具有由$ n $界定的积分速率参数。我们的第二种方法使用代数和组合工具,并适用于具有共享试验参数$ n $的二项式混合物以及不同的成功参数,以及几何分布的混合物。同样,例如,对于具有$ k $组件的二项式混合物和成功参数,分配为分辨率$ε$,$ o(k^2(n/ε)^{8/\sqrtε})$样本足以精确地恢复参数。对于其中一些分布,我们的结果代表了参数估计的第一个保证。
We present two different approaches for parameter learning in several mixture models in one dimension. Our first approach uses complex-analytic methods and applies to Gaussian mixtures with shared variance, binomial mixtures with shared success probability, and Poisson mixtures, among others. An example result is that $\exp(O(N^{1/3}))$ samples suffice to exactly learn a mixture of $k<N$ Poisson distributions, each with integral rate parameters bounded by $N$. Our second approach uses algebraic and combinatorial tools and applies to binomial mixtures with shared trial parameter $N$ and differing success parameters, as well as to mixtures of geometric distributions. Again, as an example, for binomial mixtures with $k$ components and success parameters discretized to resolution $ε$, $O(k^2(N/ε)^{8/\sqrtε})$ samples suffice to exactly recover the parameters. For some of these distributions, our results represent the first guarantees for parameter estimation.