arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1502.06189stat.MLcs.LG
收藏

两阶段抽样、预测和相关筛选自适应回归(SPARCS)

Two-stage Sampling, Prediction and Adaptive Regression via Correlation Screening (SPARCS)

Hamed Firouzi, Alfred Hero, Bala Rajaratnam

摘要:

本文提出了一种适用于高维有限预测量设计的自适应方法,称为两阶段抽样、预测和相关筛选自适应回归(SPARCS)。SPARCS可以应用于实验科学、医学、金融和工程中的高维预测问题,如下所示。假设希望运行一系列实验以基于独立变量$\mathbf X=[X_1,\ldots, X_p]^T$(测定的生物标志物)的$p$维度集合来学习因变量$Y$(例如疾病预后)的稀疏多变量预测器。假设获取变量$\mathbf X$的完整集合的成本在其维度上线性增加。SPARCS将数据收集分为两个阶段,以实现采样成本和预测性能之间的最佳权衡。在第一阶段中,我们收集了几个($n$)昂贵的样本$\{y_i,\mathbf x_i\}_{i=1}^n$,在全维$p\gg n$的$\mathbf X$,筛选的变量数量下降到一个较小的维度$l < p$使用类型的互相关或回归系数筛选。在第二阶段,我们收集了大量的$(t-n)$的$l$变量,通过第一阶段的筛选更便宜的样本。在第二阶段,通过使用所选变量的所有$t$样本求解标准回归问题来构造低维预测器。SPARCS是一种自适应的在线算法,对选定的变量进行假阳性控制,非常适合小样本,并且可扩展到高维。我们建立渐近界的Familywise错误率(FWER),指定高维收敛率的支持恢复,并建立最佳的样本分配规则的第一和第二阶段。

英文摘要:

This paper proposes a general adaptive procedure for budget-limited predictor design in high dimensions called two-stage Sampling, Prediction and Adaptive Regression via Correlation Screening (SPARCS). SPARCS can be applied to high dimensional prediction problems in experimental science, medicine, finance, and engineering, as illustrated by the following. Suppose one wishes to run a sequence of experiments to learn a sparse multivariate predictor of a dependent variable $Y$ (disease prognosis for instance) based on a $p$ dimensional set of independent variables $\mathbf X=[X_1,\ldots, X_p]^T$ (assayed biomarkers). Assume that the cost of acquiring the full set of variables $\mathbf X$ increases linearly in its dimension. SPARCS breaks the data collection into two stages in order to achieve an optimal tradeoff between sampling cost and predictor performance. In the first stage we collect a few ($n$) expensive samples $\{y_i,\mathbf x_i\}_{i=1}^n$, at the full dimension $p\gg n$ of $\mathbf X$, winnowing the number of variables down to a smaller dimension $l < p$ using a type of cross-correlation or regression coefficient screening. In the second stage we collect a larger number $(t-n)$ of cheaper samples of the $l$ variables that passed the screening of the first stage. At the second stage, a low dimensional predictor is constructed by solving the standard regression problem using all $t$ samples of the selected variables. SPARCS is an adaptive online algorithm that implements false positive control on the selected variables, is well suited to small sample sizes, and is scalable to high dimensions. We establish asymptotic bounds for the Familywise Error Rate (FWER), specify high dimensional convergence rates for support recovery, and establish optimal sample allocation rules to the first and second stages.

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。

↑