3

This is a reference request. Strong convexity of the loss function is often used in theoretical analyses of convex optimisation for machine learning. My question is, are there important / widely used loss functions (or cost functions) being used in machine learning in practice? I know of the logistic loss for classification, and the square loss for regression. Are there any others?

axk
  • 736
  • 4
  • 14

1 Answers1

1

Another example is Hinge loss used in SVM.

Related post

Also, L1 related loss: least absolute loss.

Combination between L1 and L2 regularization (https://en.wikipedia.org/wiki/Elastic_net_regularization).

Haitao Du
  • 32,885
  • 17
  • 118
  • 213