Paper pick
The ability of an ML model to deal with noisy training data depends in great part on the loss function used in the training process. For classification tasks, the standard loss function used for training is the logistic loss. However, the logistic loss function falls short when handling noisy training examples due to two properties:
- Outliers far away can dominate the overall loss
- Mislabeled examples nearby can stretch the decision boundary
Google Research tackles these problems in a recent paper by introducing a “bi-tempered” generalization of the logistic loss endowed with two tunable parameters that handle those situations well.
|