No Free Lunch Theorem
In mathematical folklore, the "no free lunch" theorem (sometimes pluralized) of Wolpert and Macready appears in the 1997 "No Free Lunch Theorems for Optimization." Wolpert had previously derived no free lunch theorems for machine learning (statistical inference). In 2005, Wolpert and Macready themselves indicated that the first theorem in their paper "state that any two optimization algorithms are equivalent when their performance is averaged across all possible problems." The 1997 theorems of Wolpert and Macready are mathematically technical and some find them unintuitive. The folkloric "no free lunch" (NFL) theorem is an easily stated and easily understood consequence of theorems Wolpert and Macready actually prove. It is weaker than the proven theorems, and thus does not encapsulate them.
Various investigators have extended the work of Wolpert and Macready substantively. See No free lunch in search and optimization for treatment of the research area.
Read more about No Free Lunch Theorem: Original NFL Theorems, Intelligent Design and The NFL Theorem
Famous quotes containing the words free, lunch and/or theorem:
“The American adolescent, then, is faced, as are the adolescents of all countries who have entered or are entering the machine age, with the question: freedom from what and at what price? The American feels so rich in his opportunities for free expression that he often no longer knows what it is he is free from. Neither does he know where he is not free; he does not recognize his native autocrats when he sees them.”
—Erik H. Erikson (1904–1994)
“Long as there’s lunch counters, you can always find work.”
—Mother and Aunts Of Dorothy Allison, U.S. waitresses. As quoted in Skin, ch. 2, by Dorothy Allison (1994)
“To insure the adoration of a theorem for any length of time, faith is not enough, a police force is needed as well.”
—Albert Camus (1913–1960)