Learning Balanced Mixtures of Discrete Distributions with Small Sample

dc.creatorZhou, Shuheng
dc.date2008-02-10
dc.date.accessioned2026-07-07T09:21:54Z
dc.date.available2026-07-07T09:21:54Z
dc.descriptionWe study the problem of partitioning a small sample of $n$ individuals from a mixture of $k$ product distributions over a Boolean cube $\{0, 1\}^K$ according to their distributions. Each distribution is described by a vector of allele frequencies in $\R^K$. Given two distributions, we use $γ$ to denote the average $\ell_2^2$ distance in frequencies across $K$ dimensions, which measures the statistical divergence between them. We study the case assuming that bits are independently distributed across $K$ dimensions. This work demonstrates that, for a balanced input instance for $k = 2$, a certain graph-based optimization function returns the correct partition with high probability, where a weighted graph $G$ is formed over $n$ individuals, whose pairwise hamming distances between their corresponding bit vectors define the edge weights, so long as $K = Ω(\ln n/γ)$ and $Kn = \tildeΩ(\ln n/γ^2)$. The function computes a maximum-weight balanced cut of $G$, where the weight of a cut is the sum of the weights across all edges in the cut. This result demonstrates a nice property in the high-dimensional feature space: one can trade off the number of features that are required with the size of the sample to accomplish certain tasks like clustering.
dc.description24 Pages, 5 figures
dc.identifierhttps://arxiv.org/abs/0802.1244
dc.identifierhttp://arxiv.org/abs/0802.1244
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/155190
dc.subjectMachine Learning
dc.titleLearning Balanced Mixtures of Discrete Distributions with Small Sample
dc.typetext

Files

Collections