Loss Function - Decision Rules

Decision Rules

A decision rule makes a choice using an optimality criterion. Some commonly used criteria are:

  • Minimax: Choose the decision rule with the lowest worst loss — that is, minimize the worst-case (maximum possible) loss:
  • Invariance: Choose the optimal decision rule which satisfies an invariance requirement.
  • Choose the decision rule with the lowest average loss (i.e. minimize the expected value of the loss function):

Read more about this topic:  Loss Function

Famous quotes containing the words decision and/or rules:

    “Once the decision has been reached, close your ears even to the best counter-argument: a sign of strong character. Thus an occasional will to stupidity.”
    —Friedrich Nietzsche (1844–1900)

    “However patriarchal the world, at home the child knows that his mother is the source of all power. The hand that rocks the cradle rules his world. . . . The son never forgets that he owes his life to his mother, not just the creation of it but the maintenance of it, and that he owes her a debt he cannot conceivably repay, but which she may call in at any time.”
    —Frank Pittman (20th century)