论文标题
在深层图像分类器中分配可靠的多类分类和应用
Distributionally Robust Multiclass Classification and Applications in Deep Image Classifiers
论文作者
论文摘要
我们为多类logistic回归(MLR)开发了分布强大的优化(DRO)公式,该公式可以耐受离群值污染的数据。 DRO框架使用概率歧义集,该集合定义为分布球,该分布与Wasserstein Metric的意义相近训练集的经验分布。我们将DRO公式放在正规化问题中,该问题的正规化器是系数矩阵的规范。我们为模型的解决方案建立了样本外的性能保证,提供了有关正规器在控制预测错误中作用的见解。我们将提出的方法应用于将深视觉变压器(VIT)的图像分类器鲁棒性构成随机和对抗性攻击。具体而言,使用MNIST和CIFAR-10数据集,我们通过采用一种新型的随机训练方法来证明,与基线方法相比,与基线方法相比,测试错误率最高高达83.5%,损失最高91.3%。
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.