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 I choose that my remembrances of him should be pleasing, affecting, religious. I will love him as a glorified friend, after the free way of friendship, and not pay him a stiff sign of respect, as men do to those whom they fear. A passage read from his discourses, a moving provocation to works like his, any act or meeting which tends to awaken a pure thought, a flow of love, an original design of virtue, I call a worthy, a true commemoration.”
—Ralph Waldo Emerson (1803–1882)
“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)
“His life itself passes deeper in nature than the studies of the naturalist penetrate; himself a subject for the naturalist. The latter raises the moss and bark gently with his knife in search of insects; the former lays open logs to their core with his axe, and moss and bark fly far and wide. He gets his living by barking trees. Such a man has some right to fish, and I love to see nature carried out in him.”
—Henry David Thoreau (1817–1862)