dm.cs.tu-dortmund.de/mlbits/foundations-no-free-lunch/
No Free Lunch – Lecture Notes
times, learning a target function \(f\) .
For any pair of algorithms \(a_1\) , \(a_2\) : \(\sum \nolimits _f P(d_m^y|f,m,a_1) = \sum \nolimits _f P(d_m^y|f,m,a_2)\)
…what an algorithm gains in performance [...] Macready, W.G. 1997. No free lunch theorems for optimization. IEEE Trans. Evolutionary Computation . 1, 1 (1997), 67–82. DOI: 10.1109/4235.585893
continue to Bias-Variance Tradeoff »
« return to VC Dimension …
