Consistent Robust Adversarial Prediction for General Multiclass Classification
arXiv: Machine Learning, Volume abs/1812.07526, 2018.
We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case conditional label distributions (the adversarial distributions) that (approximately) match the statistics ...More
PPT (Upload PPT)