On Continuity of Robust and Accurate Classifiers
This work addresses the trade-off between robustness and accuracy in classifiers, suggesting a shift from adversarial training to discontinuous hypotheses, which could impact the design and evaluation of ML models.
The paper argues that continuity of a hypothesis is incompatible with robustness and accuracy in machine learning, showing that continuous functions cannot learn optimal robust hypotheses, with empirical evidence that discontinuous hypotheses outperform continuous ones in common tasks.
The reliability of a learning model is key to the successful deployment of machine learning in various applications. However, it is difficult to describe the phenomenon due to the complicated nature of the problems in machine learning. It has been shown that adversarial training can improve the robustness of the hypothesis. However, this improvement usually comes at the cost of decreased performance on natural samples. Hence, it has been suggested that robustness and accuracy of a hypothesis are at odds with each other. In this paper, we put forth the alternative proposal that it is the continuity of a hypothesis that is incompatible with its robustness and accuracy in many of these scenarios. In other words, a continuous function cannot effectively learn the optimal robust hypothesis. We introduce a framework for a rigorous study of harmonic and holomorphic hypothesis in learning theory terms and provide empirical evidence that continuous hypotheses do not perform as well as discontinuous hypotheses in some common machine learning tasks. From a practical point of view, our results suggests that a robust and accurate learning rule would train different continuous hypotheses for different regions of the domain. From a theoretical perspective, our analysis explains the adversarial examples phenomenon in these situations as a conflict between the continuity of a sequence of functions and its uniform convergence to a discontinuous function. Given that many of the contemporary machine learning models are continuous functions, it is important to theoretically study the continuity of robust and accurate classifiers as it is consequential in their construction, analysis and evaluation.