Experimental results showthattheproposed metriclearning algorithm improves both certified robust errors and empirical robust errors (errors under adversarial attacks).

Forsuch models, one particularly elegant approach is that ofpassive-aggressive learning[3]. In this framework, a model isonly updated when itfails to classify an example correctly with high confidence.

This is the appendix of the paper " Quantification of Uncertainty with Adversarial Models ". It consists of three sections.

Quantifying uncertainty is important for actionable predictions in real-world applications.

Each step replaces the two mostsimilar clusters by its union.

The excess risk bound achieves the so-called fast learning rate.