1. The joy of Entropy

2. Administrivia Reminder: HW 1 due next week No other news. No noose is good noose...

3. Time wings on... Last time: Hypothesis spaces Intro to decision trees This time: Learning bias The getBestSplitFeature function Entropy

4. Back to decision trees... Reminders: Hypothesis space for DT: Data struct view: All trees with single test per internal node and constant leaf value Geometric view: Sets of axis-orthagonal hyper-rectangles; piecewise constant approximation Open question: getBestSplitFeature function

5. Splitting criteria What properties do we want our getBestSplitFeature() function to have? Increase the purity of the data After split, new sets should be closer to uniform labeling than before the split Want the subsets to have roughly the same purity Want the subsets to be as balanced as possible

6. Bias These choices are designed to produce small trees May miss some other, better trees that are: Larger Require a non-greedy split at the root Definition: Learning bias == tendency of an algorithm to find one class of solution out of H in preference to another

7. Bias: the pretty picture Space of all functions on

8. Bias: the algebra Bias also seen as expected difference between true concept and induced concept: Note: expectation taken over all possible data sets Don’t actually know that distribution either :-P Can (sometimes) make a prior assumption

9. More on Bias Bias can be a property of: Risk/loss function How you measure “distance” to best solution Search strategy How you move through H to find

10. Back to splitting... Consider a set of true/false labels Want our measure to be small when the set is pure (all true or all false), and large when set is almost evenly divided between the classes In general: we call such a function impurity, i(y) We’ll use entropy Expresses the amount of information in the set (Later we’ll use the negative of this function, so it’ll be better if the set is almost pure)

11. Entropy, cont’d Define: class fractions (a.k.a., class prior probabilities)

12. Entropy, cont’d Define: class fractions (a.k.a., class prior probabilities) Define: entropy of a set

13. Entropy, cont’d Define: class fractions (a.k.a., class prior probabilities) Define: entropy of a set In general, for classes :

14. The entropy curve

15. Properties of entropy Maximum when class fractions equal Minimum when data is pure Smooth Differentiable; continuous Convex Intuitively: entropy of a dist tells you how “predictable” that dist is.

16. Entropy in a nutshell From: Andrew Moore’s tutorial on information gain: http://www.cs.cmu.edu/~awm/tutorials

17. Entropy in a nutshell data values (location of soup) sampled from tight distribution (bowl) -- highly predictable Low entropy distribution

18. Entropy in a nutshell data values (location of soup) sampled from loose distribution (uniformly around dining room) -- highly unpredictable High entropy distribution

19. Entropy of a split A split produces a number of sets (one for each branch) Need a corresponding entropy of a split (i.e., entropy of a collection of sets) Definition: entropy of a B -way split where:

20. Information gain The last, easy step: Want to pick the attribute that decreases the information content of the data as much as possible Q: Why decrease? Define: gain of splitting data set [X,y] on attribute a :

21. The splitting method Feature getBestSplitFeature(X,Y) { // Input: instance set X, label set Y double baseInfo=entropy(Y); double[] gain=new double[]; for (a : X.getFeatureSet()) { [X0,...,Xk,Y0,...,Yk]=a.splitData(X,Y); gain[a]=baseInfo-splitEntropy(Y0,...,Yk); } return argmax(gain); }

22. DTs in practice... Growing to purity is bad (overfitting)

23. DTs in practice... Growing to purity is bad (overfitting) x1: petal length x2: sepal width

24. DTs in practice... Growing to purity is bad (overfitting) x1: petal length x2: sepal width

25. DTs in practice... Growing to purity is bad (overfitting) Terminate growth early Grow to purity, then prune back

26. DTs in practice... Growing to purity is bad (overfitting) x1: petal length x2: sepal width Not statistically supportable leaf Remove split & merge leaves

27. DTs in practice... Multiway splits are a pain Entropy is biased in favor of more splits Correct w/ gain ratio (DH&S Ch. 8.3.2, Eqn 7)

28. DTs in practice... Real-valued attributes rules of form if (x1<3.4) {... } How to pick the “3.4”?