Revision as of 08:24, 5 October 2021 edit DaFilipo (talk \| contribs) 1 edit m change link "Active Learning" to active learning in the context of machine learning: "Active learning (machine learning)". Tag: Visual edit ← Previous edit		Revision as of 06:49, 31 October 2021 edit undo 104.156.64.158 (talk) No edit summary Next edit →
Line 8: * The strong variant takes the worst-case sample complexity over all input-output distributions. The [[No ~~Free~~free ~~Lunch~~lunch theorem]], discussed below, proves that, in general, the strong sample complexity is infinite, i.e. that there is no algorithm that can learn the globally-optimal target function using a finite number of training samples. However, if we are only interested in a particular class of target functions (e.g, only linear functions) then the sample complexity is finite, and it depends linearly on the [[VC dimension]] on the class of target functions.<ref name=":0" />

Sample complexity: Difference between revisions