We develop a Distributionally Robust Optimization (DRO) formulation for Multiclass Logistic Regression (MLR), which could tolerate data contaminated by outliers. The DRO framework uses a probabilistic ambiguity set defined as a ball of distributions that are close to the empirical distribution of the training set in the sense of the Wasserstein metric. We relax the DRO formulation into a regularized learning problem whose regularizer is a norm of the coefficient matrix. We establish out-of-sample performance guarantees for the solutions to our model, offering insights on the role of the regularizer in controlling the prediction error. We apply the proposed method in rendering deep Vision Transformer (ViT)-based image classifiers robust to random and adversarial attacks. Specifically, using the MNIST and CIFAR-10 datasets, we demonstrate reductions in test error rate by up to 83.5% and loss by up to 91.3% compared with baseline methods, by adopting a novel random training method.
翻译:我们为多类逻辑回归(MLR)开发了一个分布鲁棒优化(DRO)公式,可以容忍被异常值污染的数据。DRO框架使用一个概率的歧义集,它被定义为一个球形分布的集合,这些分布在Wasserstein度量意义下与训练集的经验分布相近。我们将DRO公式放宽到一个正则化学习问题中,其正则化器为系数矩阵的范数。我们为我们模型的解决方案确立了样外表现保证,从而深入研究了正则化器在控制预测误差方面的作用。我们在深度视觉Transformer(ViT)图像分类器中应用了所提出的方法,使其能够抵抗随机和对抗攻击。具体来说,使用MNIST和CIFAR-10数据集,我们通过采用一种新颖的随机训练方法,在测试错误率和损失方面将其与基线方法相比较,分别减少了83.5%和91.3%。