There are free lunches
No-Free-Lunch Theorems state that the performance of all algorithms is the same when averaged over all possible tasks. It has been argued that the necessary conditions for NFL are too restrictive to be found in practice. There must be some information for a set of tasks that ensures some algorithms perform better than others. In this paper we propose a novel idea, "There are free lunches" (TAFL) Theorem, which states that some algorithms can achieve the best performance in all possible tasks, in the condition that tasks are given in a specific order. Furthermore, we point out that with the number of solved tasks increasing, the difficulty of solving a new task decreases. We also present an example to explain how to combine the proposed theorem and the existing supervised learning algorithms.
PDF Abstract