No Free Lunch In Search And Optimization
In computing, there are circumstances in which the outputs of all procedures solving a particular type of problem are statistically identical. A colorful way of describing such a circumstance, introduced by David Wolpert and William G. Macready in connection with the problems of search and optimization, is to say that there is no free lunch. Wolpert had previously derived no free lunch theorems for machine learning (statistical inference). Before Wolpert's article was published, Cullen Schaffer had summarized a preprint version of this work of Wolpert's, but used different terminology.
In the "no free lunch" metaphor, each "restaurant" (problem-solving procedure) has a "menu" associating each "lunch plate" (problem) with a "price" (the performance of the procedure in solving the problem). The menus of restaurants are identical except in one regard – the prices are shuffled from one restaurant to the next. For an omnivore who is as likely to order each plate as any other, the average cost of lunch does not depend on the choice of restaurant. But a vegan who goes to lunch regularly with a carnivore who seeks economy pays a high average cost for lunch. To methodically reduce the average cost, one must use advance knowledge of a) what one will order and b) what the order will cost at various restaurants. That is, improvement of performance in problem-solving hinges on using prior information to match procedures to problems.
In formal terms, there is no free lunch when the probability distribution on problem instances is such that all problem solvers have identically distributed results. In the case of search, a problem instance is an objective function, and a result is a sequence of values obtained in evaluation of candidate solutions in the domain of the function. For typical interpretations of results, search is an optimization process. There is no free lunch in search if and only if the distribution on objective functions is invariant under permutation of the space of candidate solutions. This condition does not hold precisely in practice, but an "(almost) no free lunch" theorem suggests that it holds approximately.
Read more about No Free Lunch In Search And Optimization: Overview, No Free Lunch (NFL), Formal Synopsis of NFL, Original NFL Theorems, Interpretations of NFL Results, Coevolutionary Free Lunches
Famous quotes containing the words free, lunch and/or search:
“For myself I found that the occupation of a day-laborer was the most independent of any, especially as it required only thirty or forty days in a year to support one. The laborers day ends with the going down of the sun, and he is then free to devote himself to his chosen pursuit, independent of his labor; but his employer, who speculates from month to month, has no respite from one end of the year to the other.”
—Henry David Thoreau (18171862)
“Women who are devoted to causes, such as overpopulation and the underprivileged [sic], are much less interested in fashion than, lets say, those who lunch at La Grenouille and Le Cirque.”
—Ann Landers (b. 1918)
“At any age we must cherish illusions, consolatory or merely pleasant; in youth, they are omnipresent; in old age we must search for them, or even invent them. But with all that, boredom is their natural and inevitable accompaniment.”
—Philip Dormer Stanhope, 4th Earl Chesterfield (16941773)