Deep Learning is Provably Robust to Symmetric Label Noise

Deep neural networks (DNNs) are capable of perfectly fitting the training data, including memorizing noisy data. It is commonly believed that memorization hurts generalization. Therefore, many recent works propose mitigation strategies to avoid noisy data or correct memorization. In this work, we step back and ask the question: Can deep learning be robust against massive label noise without any mitigation? We provide an affirmative answer for the case of symmetric label noise: We find that certain DNNs, including under-parameterized and over-parameterized models, can tolerate massive symmetric label noise up to the information-theoretic threshold. By appealing to classical statistical theory and universal consistency of DNNs, we prove that for multiclass classification, $L_1$-consistent DNN classifiers trained under symmetric label noise can achieve Bayes optimality asymptotically if the label noise probability is less than $\frac{K-1}{K}$, where $K \ge 2$ is the number of classes. Our results show that for symmetric label noise, no mitigation is necessary for $L_1$-consistent estimators. We conjecture that for general label noise, mitigation strategies that make use of the noisy data will outperform those that ignore the noisy data.