Classification with Asymmetric Label Noise: Consistency and Maximal Denoising

no code implementations • 5 Mar 2013 • Gilles Blanchard, Marek Flaska, Gregory Handy, Sara Pozzi, Clayton Scott

For any label noise problem, there is a unique pair of true class-conditional distributions satisfying the proposed conditions, and we argue that this pair corresponds in a certain sense to maximal denoising of the observed distributions.

Classification Denoising +1