Machine Learning CUNY Graduate Center Lecture 4: Logistic Regression.

Machine Learning

CUNY Graduate Center

Lecture 4: Logistic Regression

Today

• Linear Regression– Bayesians v. Frequentists– Bayesian Linear Regression

• Logistic Regression– Linear Model for Classification

2

Regularization: Penalize large weights

• Introduce a penalty term in the loss function.

3

Regularized Regression(L2-Regularization or Ridge Regression)

More regularization

• The penalty term defines the styles of regularization

• L2-Regularization• L1-Regularization• L0-Regularization

– L0-norm is the optimal subset of features

4

Curse of dimensionality

• Increasing dimensionality of features increases the data requirements exponentially.

• For example, if a single feature can be accurately approximated with 100 data points, to optimize the joint over two features requires 100*100 data points.

• Models should be small relative to the amount of available data

• Dimensionality reduction techniques – feature selection – can help.– L0-regularization is explicit feature selection– L1- and L2-regularizations approximate feature selection.

5

Bayesians v. Frequentists

• What is a probability?• Frequentists

– A probability is the likelihood that an event will happen– It is approximated by the ratio of the number of observed events to the

number of total events– Assessment is vital to selecting a model– Point estimates are absolutely fine

• Bayesians– A probability is a degree of believability of a proposition.– Bayesians require that probabilities be prior beliefs conditioned on data.– The Bayesian approach “is optimal”, given a good model, a good prior

and a good loss function. Don’t worry so much about assessment.– If you are ever making a point estimate, you’ve made a mistake. The

only valid probabilities are posteriors based on evidence given some prior

6

Bayesian Linear Regression

• The previous MLE derivation of linear regression uses point estimates for the weight vector, w.

• Bayesians say, “hold it right there”.– Use a prior distribution over w to estimate parameters

• Alpha is a hyperparameter over w, where alpha is the precision or inverse variance of the distribution.

• Now optimize:

7

Optimize the Bayesian posterior

8

As usual it’s easier to optimize after a log transform.

Optimize the Bayesian posterior

9

As usual it’s easier to optimize after a log transform.

Optimize the Bayesian posterior

10

Ignoring terms that do not depend on w

IDENTICAL formulation as L2-regularization

Context

• Overfitting is bad.

• Bayesians vs. Frequentists– Is one better?– Machine Learning uses techniques from both

camps.

11

Logistic Regression

• Linear model applied to classification

• Supervised: target information is available– Each data point xi has a corresponding target

ti.

• Goal: Identify a function

12

Target Variables

• In binary classification, it is convenient to represent ti as a scalar with a range of [0,1]– Interpretation of ti as the likelihood that xi is the member of

the positive class– Used to represent the confidence of a prediction.

• For L > 2 classes, ti is often represented as a K element vector. – tij represents the degree of membership in class j.– |ti| = 1– E.g. 5-way classification vector:

13

Graphical Example of Classification

14

Decision Boundaries

15

Graphical Example of Classification

16

Classification approaches

• Generative– Models the joint distribution

between c and x– Highest data requirements

• Discriminative– Fewer parameters to approximate

• Discriminant Function– May still be trained probabilistically,

but not necessarily modeling a likelihood.

17

Treating Classification as a Linear model

18

Relationship between Regression and Classification

• Since we’re classifying two classes, why not set one class to ‘0’ and the other to ‘1’ then use linear regression.– Regression: -infinity to infinity, while class labels

are 0, 1• Can use a threshold, e.g.

– y >= 0.5 then class 1– y < 0.5 then class 2

19

f(x)>=0.5?

Happy/Good/ClassA

Sad/Not Good/ClassB

1

Odds-ratio

• Rather than thresholding, we’ll relate the regression to the class-conditional probability.

• Ratio of the odd of prediction y = 1 or y = 0– If p(y=1|x) = 0.8 and p(y=0|x) = 0.2– Odds ratio = 0.8/0.2 = 4

• Use a linear model to predict odds rather than a class label.

20

Logit – Log odds ratio function

• LHS: 0 to infinity• RHS: -infinity to

infinity• Use a log function.

– Has the added bonus of disolving the division leading to easy manipulation

21

Logistic Regression

• A linear model used to predict log-odds ratio of two classes

22

Logit to probability

23

Sigmoid function

• Squashing function to map the reals to a finite domain.

24

Gaussian Class-conditional

• Assume the data is generated from a gaussian distribution for each class.

• Leads to a bayesian formulation of logistic regression.

25

Bayesian Logistic Regression

26

Maximum Likelihood ExtimationLogistic Regression

• Class-conditional Gaussian.

• Multinomial Class distribution.

• As ever, take the derivative of this likelihood function w.r.t.

27

Maximum Likelihood Estimation of the prior

28

Maximum Likelihood Estimation of the prior

29

Maximum Likelihood Estimation of the prior

30

Discriminative Training

• Take the derivatives w.r.t. – Be prepared for this for homework.

• In the generative formulation, we need to estimate the joint of t and x.– But we get an intuitive regularization

technique.

• Discriminative Training– Model p(t|x) directly.

31

What’s the problem with generative training

• Formulated this way, in D dimensions, this function has D parameters.

• In the generative case, 2D means, and D(D+1)/2 covariance values

• Quadratic growth in the number of parameters.

• We’d rather linear growth.

32

Discriminative Training

33

Optimization

• Take the gradient in terms of w

34

Optimization

35

Optimization

36

Optimization

37

Optimization: putting it together

38

Optimization

• We know the gradient of the error function, but how do we find the maximum value?

• Setting to zero is nontrivial

• Numerical approximation

39

Gradient Descent

• Take a guess.

• Move in the direction of the negative gradient

• Jump again.

• In a convex function this will converge

• Other methods include Newton-Raphson40

Multi-class discriminant functions

• Can extend to multiple classes

• Other approaches include constructing K-1 binary classifiers.

• Each classifier compares cn to not cn

• Computationally simpler, but not without problems

41

Exponential Model

• Logistic Regression is a type of exponential model.– Linear combination of weights and features to

produce a probabilistic model.

42

Problems with Binary Discriminant functions

43

K-class discriminant

44

Entropy

• Measure of uncertainty, or Measure of “Information”

• High uncertainty equals high entropy.

• Rare events are more “informative” than common events.

45

Entropy

• How much information is received when observing ‘x’?

• If independent, p(x,y) = p(x)p(y).– H(x,y) = H(x) + H(y)– The information contained in two unrelated

events is equal to their sum.

46

Entropy

• Binary coding of p(x): -log p(x)– “How many bits does it take to represent a

value p(x)?”– How many “decimal” places? How many

binary decimal places?

• Expected value of observed information

47

Examples of Entropy

• Uniform distributions have higher distributions.

48

Maximum Entropy

• Logistic Regression is also known as Maximum Entropy.

• Entropy is convex.– Convergence Expectation.

• Constrain this optimization to enforce good classification.

• Increase maximum likelihood of the data while making the distribution of weights most even.– Include as many useful features as possible.

49

Maximum Entropy with Constraints

• From Klein and Manning Tutorial50

Optimization formulation

• If we let the weights represent likelihoods of value for each feature.

51

For each feature i

Solving MaxEnt formulation

• Convex optimization with a concave objective function and linear constraints.

• Lagrange Multipliers

52

For each feature iDual representation of the

maximum likelihood estimation of Logistic Regression

Dual representation of the maximum likelihood estimation of

Logistic Regression

Summary

• Bayesian Regularization– Introduction of a prior over parameters serves to

constrain weights

• Logistic Regression– Log odds to construct a linear model– Formulation with Gaussian Class Conditionals– Discriminative Training– Gradient Descent

• Entropy– Logistic Regression as Maximum Entropy.

53

Next Time

• Graphical Models

• Read Chapter 8.1, 8.2

54