A loss function is a real lower-bounded function L on Θ × A for some θ ∈ Θ. The value L(θ, δ(X)) is the cost of action δ(X) under parameter θ.
Read more about Loss Function: Decision Rules, Expected Loss, Selecting A Loss Function, Loss Functions in Bayesian Statistics, Regret, Quadratic Loss Function, 0-1 Loss Function
Famous quotes containing the words loss and/or function:
“Mothers risk alienating their mates if they expect them to hold or care for the baby exactly as they do. Fathers who are constantly criticized or corrected may lose interest in handling the baby, and this is a loss for everyone. The cycle is a dangerous one. Now the same mother feels bitter because she is no longer getting any help at home.”
—Cathy Rindner Tempelsman (20th century)
“Uses are always much broader than functions, and usually far less contentious. The word function carries overtones of purpose and propriety, of concern with why something was developed rather than with how it has actually been found useful. The function of automobiles is to transport people and objects, but they are used for a variety of other purposes—as homes, offices, bedrooms, henhouses, jetties, breakwaters, even offensive weapons.”
—Frank Smith (b. 1928)