Random-Forest on The Standard Errorhttps://jongha-jeon-dev.github.io/standarderror/tags/random-forest/Recent content in Random-Forest on The Standard ErrorHugo -- 0.123.7en-gbMon, 12 Oct 2026 00:00:00 +0000ML 9: The Bias–Variance U Belongs to a Knob, Not to Complexityhttps://jongha-jeon-dev.github.io/standarderror/lectures/ml-9-bias-variance/Thu, 08 Oct 2026 00:00:00 +0000https://jongha-jeon-dev.github.io/standarderror/lectures/ml-9-bias-variance/Test error is said to be U-shaped in model complexity. Computed exactly, it is for the number of neighbours and is not for the number of trees: one knob trades bias for variance, the other only averages.ML 12: Impurity Importance Rewards Features With Many Places to Splithttps://jongha-jeon-dev.github.io/standarderror/lectures/ml-12-impurity/Mon, 12 Oct 2026 00:00:00 +0000https://jongha-jeon-dev.github.io/standarderror/lectures/ml-12-impurity/A forest's default feature importance is computed on the data it was fitted to. On a design where the answer is known, it never ranks the only useful feature first, and ranks it last in 19 of 20 datasets.ML 13: Out-of-Bag Error Is Free, Pessimistic When Small and Blind to Copieshttps://jongha-jeon-dev.github.io/standarderror/lectures/ml-13-oob/Mon, 12 Oct 2026 00:00:00 +0000https://jongha-jeon-dev.github.io/standarderror/lectures/ml-13-oob/A random forest estimates its own test error from the rows each tree did not see. With enough trees that is as good as cross-validation, for a sixth of the work. With few trees, or rows that are not independent, it is not.ML 15: A Forest Cannot Predict Beyond the Largest Value It Has Seenhttps://jongha-jeon-dev.github.io/standarderror/lectures/ml-15-extrapolation/Mon, 12 Oct 2026 00:00:00 +0000https://jongha-jeon-dev.github.io/standarderror/lectures/ml-15-extrapolation/Tree ensembles are said to approximate any function. Inside the training range they do; outside it their predictions go flat, below the largest label they saw, and the best single model becomes the worst.