Two Broad Classes of Functions for Which a No Free Lunch Result Does Not Hold
نویسنده
چکیده
We identify classes of functions for which a No Free Lunch result does and does not hold, with particular emphasis on the relationship between No Free Lunch and problem description length. We show that a NFL result does not apply to a set of functions when the description length of the functions is sufficiently bounded. We consider sets of functions with non-uniform associated probability distributions, and show that a NFL result does not hold if the probabilities are assigned according either to description length or to a Solomonoff-Levin distribution. We close with a discussion of the conditions under which NFL can apply to sets containing an infinite number of functions.
منابع مشابه
On Classes of Functions for which No Free Lunch Results Hold
In a recent paper [3] it was shown that No Free Lunch results [5] hold for any subset F of the set of all possible functions from a finite set X to a finite set Y iff F is closed under permutation of X . In this article, we prove that the number of those subsets can be neglected compared to the overall number of possible subsets. Further, we present some arguments why problem classes relevant i...
متن کاملA No-Free-Lunch theorem for non-uniform distributions of target functions
The sharpened No-Free-Lunch-theorem (NFL-theorem) states that, regardless of the performance measure, the performance of all optimization algorithms averaged uniformly over any finite set F of functions is equal if and only if F is closed under permutation (c.u.p.). In this paper, we first summarize some consequences of this theorem, which have been proven recently: The number of subsets c.u.p....
متن کاملRecent Results on No-Free-Lunch Theorems for Optimization
The sharpened No-Free-Lunch-theorem (NFL-theorem) states that the performance of all optimization algorithms averaged over any finite set F of functions is equal if and only if F is closed under permutation (c.u.p.) and each target function in F is equally likely. In this paper, we first summarize some consequences of this theorem, which have been proven recently: The average number of evaluati...
متن کاملA two-phase free boundary problem for a semilinear elliptic equation
In this paper we study a two-phase free boundary problem for a semilinear elliptic equation on a bounded domain $Dsubset mathbb{R}^{n}$ with smooth boundary. We give some results on the growth of solutions and characterize the free boundary points in terms of homogeneous harmonic polynomials using a fundamental result of Caffarelli and Friedman regarding the representation of functions whose ...
متن کاملSome Multiobjective Optimizers are Better than Others
The No-Free-Lunch (NFL) theorems hold for general multiobjective fitness spaces, in the sense that, over a space of problems which is closed under permutation, any two algorithms will produce the same set of multiobjective samples. However, there are salient ways in which NFL does not generally hold in multiobjective optimization. Previously we have shown that a ‘free lunch’ can arise when comp...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2003