arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.13832cs.DScs.LG
收藏

最坏期望误差的快速算法和恒定下界

Faster Algorithms and Constant Lower Bounds for the Worst-Case Expected Error

Chalmers University of Technology(查尔姆斯理工大学)

Jonah Brown-Cohen

摘要:

Chen、Valiant和Valiant最近介绍了在不对数据值进行分布假设的情况下,但了解数据汇集方法的统计估计研究(NeurIPS 2020)。在这个框架中,我们的目标是设计估计,最大限度地减少最坏情况下的预期误差。这里的预期是在来自某些群体的已知随机数据汇集过程中,并且与群体的每个元素相对应的数据值被假设为最差情况。Chen,Valiant和Valiant表明,当数据值是$\ell_{\infty}$ -归一化的,有一个多项式时间算法来计算估计的平均值与最坏情况下的预期误差是在一个因素$\fracπ{2}$内的最佳自然类的半线性估计。然而,他们的算法是基于优化一个有点复杂的凹目标函数在一组约束的半正定矩阵,因此没有明确的运行时间保证,除了多项式时间的输入。在本文中,我们设计了可证明有效的算法来逼近基于在线凸优化的最优半线性估计。在设置中的数据值是$\ell_{\infty}$规范化,我们的算法实现了一个$\fracπ{2}$近似迭代求解一系列标准的SDP。当数据值是$\ell_2$规范化的,我们的算法迭代计算矩阵序列的顶部特征向量,并且不丢失任何乘法近似因子。我们补充这些积极的结果,说明一个简单的组合条件,如果满足一个数据汇集过程,意味着任何(不一定是半线性)估计的平均值有恒定的最坏情况下的预期误差。

英文摘要:

The study of statistical estimation without distributional assumptions on data values, but with knowledge of data collection methods was recently introduced by Chen, Valiant and Valiant (NeurIPS 2020). In this framework, the goal is to design estimators that minimize the worst-case expected error. Here the expectation is over a known, randomized data collection process from some population, and the data values corresponding to each element of the population are assumed to be worst-case. Chen, Valiant and Valiant show that, when data values are $\ell_{\infty}$-normalized, there is a polynomial time algorithm to compute an estimator for the mean with worst-case expected error that is within a factor $\fracπ{2}$ of the optimum within the natural class of semilinear estimators. However, their algorithm is based on optimizing a somewhat complex concave objective function over a constrained set of positive semidefinite matrices, and thus does not come with explicit runtime guarantees beyond being polynomial time in the input. In this paper we design provably efficient algorithms for approximating the optimal semilinear estimator based on online convex optimization. In the setting where data values are $\ell_{\infty}$-normalized, our algorithm achieves a $\fracπ{2}$-approximation by iteratively solving a sequence of standard SDPs. When data values are $\ell_2$-normalized, our algorithm iteratively computes the top eigenvector of a sequence of matrices, and does not lose any multiplicative approximation factor. We complement these positive results by stating a simple combinatorial condition which, if satisfied by a data collection process, implies that any (not necessarily semilinear) estimator for the mean has constant worst-case expected error.

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。

↑