arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1506.07902stat.MLcs.ITmath.IT
收藏

Minimax结构正态均值推断

Minimax Structured Normal Means Inference

Akshay Krishnamurthy

摘要:

我们提供了一个统一的治疗一类广泛的嘈杂的结构恢复问题,被称为结构正常的手段问题。在这种情况下,目标是从具有不同均值的高斯分布的有限集合中识别产生一些观测数据的分布。最近的工作已经研究了几个特殊的情况下,包括稀疏向量,biclusters,和基于图形的结构。我们建立几乎匹配的上限和下限的极小极大概率的错误的任何结构化的正常手段的问题,我们推导出一个最优性证书的极大似然估计,它可以应用于许多实例。我们还考虑了一个试验设计设置,在那里我们推广我们的极大极小的界限,并推导出一个算法计算的设计策略具有一定的最优性。我们表明,我们的研究结果给出了严格的极小极大界的许多结构恢复问题,并考虑一些后果的交互式采样。

英文摘要:

We provide a unified treatment of a broad class of noisy structure recovery problems, known as structured normal means problems. In this setting, the goal is to identify, from a finite collection of Gaussian distributions with different means, the distribution that produced some observed data. Recent work has studied several special cases including sparse vectors, biclusters, and graph-based structures. We establish nearly matching upper and lower bounds on the minimax probability of error for any structured normal means problem, and we derive an optimality certificate for the maximum likelihood estimator, which can be applied to many instantiations. We also consider an experimental design setting, where we generalize our minimax bounds and derive an algorithm for computing a design strategy with a certain optimality property. We show that our results give tight minimax bounds for many structure recovery problems and consider some consequences for interactive sampling.

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。

↑