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 2403.14822stat.MLcs.LGmath.OC
收藏

使用 Sinkhorn 不确定性集的非凸鲁棒假设检验

Non-Convex Robust Hypothesis Testing using Sinkhorn Uncertainty Sets

Georgia Institute of Technology(佐治亚理工学院);University of Texas at Austin(德克萨斯大学奥斯汀分校)

Jie Wang, Rui Gao, Yao Xie

AI总结:

本文提出一种基于 Sinkhorn 不确定性集的非凸鲁棒假设检验框架,通过精确混合整数指数锥重构和凸近似方法求解最优检测器,在性能与计算效率上优于现有方法。

摘要:

我们提出了一个新框架来解决非凸鲁棒假设检验问题,其目标是寻找使最坏情况下的第一类和第二类风险函数的最大值最小化的最优检测器。基于 Sinkhorn 差异,构建了以从样本导出的经验分布为中心的分布不确定性集。鉴于目标涉及非凸、非光滑的概率函数,这些函数通常难以优化,现有方法采用近似而非精确解。为应对这一挑战,我们引入了该问题的精确混合整数指数锥重构,在输入数据量适中的情况下可求解至全局最优。随后,我们提出了一种凸近似,证明了其优于文献中现有的最先进方法。此外,我们建立了鲁棒假设检验与非鲁棒风险函数正则化形式之间的联系,提供了深刻的解释。我们的数值研究突出了所提出框架令人满意的检验性能和计算效率。

英文摘要:

We present a new framework to address the non-convex robust hypothesis testing problem, wherein the goal is to seek the optimal detector that minimizes the maximum of worst-case type-I and type-II risk functions. The distributional uncertainty sets are constructed to center around the empirical distribution derived from samples based on Sinkhorn discrepancy. Given that the objective involves non-convex, non-smooth probabilistic functions that are often intractable to optimize, existing methods resort to approximations rather than exact solutions. To tackle the challenge, we introduce an exact mixed-integer exponential conic reformulation of the problem, which can be solved into a global optimum with a moderate amount of input data. Subsequently, we propose a convex approximation, demonstrating its superiority over current state-of-the-art methodologies in literature. Furthermore, we establish connections between robust hypothesis testing and regularized formulations of non-robust risk functions, offering insightful interpretations. Our numerical study highlights the satisfactory testing performance and computational efficiency of the proposed framework.

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。

↑