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 1402.0830math.STmath.PRstat.TH
收藏

凸约束下最小二乘问题的一个新视角

A new perspective on least squares under convex constraint

Sourav Chatterjee

摘要:

考虑高斯随机向量的平均值的估计问题,当假定均值向量在给定的凸集中时。最自然的解决方案是将数据向量的欧几里得投影到这个凸集上;换句话说,在凸约束下执行“最小二乘”。现代统计学和统计信号处理理论中的许多问题都是这种普遍情况的特例。例子包括套索和其他高维回归技术,函数估计问题,矩阵估计和完成,形状限制回归,约束去噪,线性逆问题等。本文给出了关于这个问题的三个一般性结果,即,(a)通过将估计误差中的主项与高斯过程的预期最大值相关联来精确计算该主项(现有的结果只给出了上界),(b)一个定理表明,在上述任何问题中,最小二乘估计在一个普适常数下总是可容许的,(c)一个反例表明,最小二乘估计不一定是最小最大速率最优的.然后使用部分(a)的结果来计算当代感兴趣的两个示例中的最小二乘估计量的误差。

英文摘要:

Consider the problem of estimating the mean of a Gaussian random vector when the mean vector is assumed to be in a given convex set. The most natural solution is to take the Euclidean projection of the data vector on to this convex set; in other words, performing "least squares under a convex constraint." Many problems in modern statistics and statistical signal processing theory are special cases of this general situation. Examples include the lasso and other high-dimensional regression techniques, function estimation problems, matrix estimation and completion, shape-restricted regression, constrained denoising, linear inverse problems, etc. This paper presents three general results about this problem, namely, (a) an exact computation of the main term in the estimation error by relating it to expected maxima of Gaussian processes (existing results only give upper bounds), (b) a theorem showing that the least squares estimator is always admissible up to a universal constant in any problem of the above kind and (c) a counterexample showing that least squares estimator may not always be minimax rate-optimal. The result from part (a) is then used to compute the error of the least squares estimator in two examples of contemporary interest.

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。

↑