AAAI Conference 2020 Short Paper
Attribute Noise Robust Binary Classification (Student Abstract)
- Aditya Petety
- Sandhya Tripathi
- N. Hemachandra
We consider the problem of learning linear classifiers when both features and labels are binary. In addition, the features are noisy, i. e. , they could be flipped with an unknown probability. In Sy-De attribute noise model, where all features could be noisy together with same probability, we show that 0-1 loss (l0−1) need not be robust but a popular surrogate, squared loss (lsq) is. In Asy-In attribute noise model, we prove that l0−1 is robust for any distribution over 2 dimensional feature space. However, due to computational intractability of l0−1, we resort to lsq and observe that it need not be Asy-In noise robust. Our empirical results support Sy- De robustness of squared loss for low to moderate noise rates.