Learning with Bad Training Data via Iterative Trimmed Loss Minimization
pp. 5739-5748, 2019.
In this paper, we study a simple and generic framework to tackle the problem of learning model parameters when a fraction of the training samples are corrupted. We first make a simple observation: in a variety of such settings, the evolution of training accuracy (as a function of training epochs) is different for clean and bad samples. ...More
PPT (Upload PPT)