Robust High-Dimensional Linear Discriminant Analysis under Training Data Contamination
Robust High-Dimensional Linear Discriminant Analysis under Training Data Contamination
复制标题
DOI：
10.1109/isit54713.2023.10206749
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Yuyang Shi;Aditya Deshmukh;Y. Mei;V. Veeravalli
中科院分区：
文献类型：
--
作者：
Yuyang Shi;Aditya Deshmukh;Y. Mei;V. Veeravalli
研究了高维稀疏线性判别分析（LDA）的鲁棒性问题，其中一部分训练数据可能被攻击者破坏。提出了一种计算效率高的算法，通过适应鲁棒均值估计沿着与LDA的校准框架。该算法的理论性质建立的最佳投影向量的估计误差和误分类率。合成和真实的数据集上的广泛的数值研究的结果报告显示，我们的算法的实用性。
The problem of robust Sparse Linear Discriminant Analysis (LDA) in high-dimensions is studied, in which a fraction of the training data may be corrupted by an adversary. A computationally efficient algorithm is proposed by adapting robust mean estimation along with a calibration framework for LDA. Theoretical properties of the proposed algorithm are established for both the estimation error of the optimal projection vector and the mis-classification rate. Results from extensive numerical studies on both synthetic and real datasets are reported to show the usefulness of our algorithm.