Memorization in Deep Neural Networks: Does the Loss Function Matter?
Deep PatelP. S. SastryPublished in: PAKDD (2) (2021)
Keyphrases
- loss function
- neural network
- pairwise
- logistic regression
- support vector
- risk minimization
- learning to rank
- reproducing kernel hilbert space
- regularization term
- boosting framework
- hinge loss
- convex loss functions
- empirical risk
- boosting algorithms
- solution path
- training process
- precision and recall
- back propagation
- bayes rule
- support vector machine