Revision as of 20:58, 27 October 2019 edit Finellach (talk \| contribs) 4 edits m →Sample-complexity bounds: Use math environment ← Previous edit		Revision as of 13:48, 26 December 2019 edit undo Thatsme314 (talk \| contribs) Extended confirmed users 7,865 edits mNo edit summary Next edit →
Line 10: The No Free 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" /> ~~<ref name=":0" />~~ ==Definition==

Sample complexity: Difference between revisions