Adversarially Robust Kernel Smoothing

Abstract

We propose a scalable robust learning algorithm combining kernel smoothing and robust optimization. Our method is motivated by the convex analysis perspective of distributionally robust optimization based on probability metrics, such as the Wasserstein distance and the maximum mean discrepancy. We adapt the integral operator using supremal convolution in convex analysis to form a novel function majorant used for enforcing robustness. Our method is simple in form and applies to general loss functions and machine learning models. Exploiting a connection with optimal transport, we prove theoretical guarantees for certified robustness under distribution shift. Furthermore, we report experiments with general machine learning models, such as deep neural networks, to demonstrate competitive performance with the state-of-the-art certifiable robust learning algorithms based on the Wasserstein distance.

References in corpus (8)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• The generalization error of random features regression: Precise asymptotics and double descent curve
• On the Convergence Proof of AMSGrad and a New Version
• Metric Learning for Adversarial Robustness
• Kernel regression in high dimensions: Refined analysis beyond double descent
• Kernel Distributionally Robust Optimization
• Distributional Robustness with IPMs and links to Regularization and GANs