Good data augmentation is one of the key factors that lead to the empiri...
Out-of-distribution (OOD) data poses serious challenges in deployed mach...
Out-of-distribution (OOD) data poses serious challenges in deployed mach...
Empirical risk minimization (ERM) is known in practice to be non-robust ...
Many modern machine learning tasks require models with high tail perform...
Many machine learning tasks involve subpopulation shift where the testin...
Understanding what information neural networks capture is an essential
p...
Adversarial training is one of the most popular ways to learn robust mod...
Neural network robustness has recently been highlighted by the existence...