Support Vector

Machine & Its

Applications

A portion (1/3) of Mingyue Tan

the slides are taken from
Prof. Andrew Moore’s
SVM tutorial at The University of British Columbia
http://www.cs.cmu.edu/~awm/tutorials
Nov 26, 2004
Overview

 Intro. to Support Vector Machines (SVM)

 Properties of SVM
 Applications
 Gene Expression Data Classification
 Text Categorization if time permits
 Discussion
Linear 
Classifiers
x f yest
f(x,w,b) = sign(w x + b)
denotes +1 w x + b>0
denotes -1

0
b=
+
x
w
How would you
classify this data?

w x + b<0
Linear 
Classifiers
x f yest
f(x,w,b) = sign(w x + b)
denotes +1
denotes -1

How would you

classify this data?
Linear 
Classifiers
x f yest
f(x,w,b) = sign(w x + b)
denotes +1
denotes -1

How would you

classify this data?
Linear 
Classifiers
x f yest
f(x,w,b) = sign(w x + b)
denotes +1
denotes -1

Any of these
would be fine..

..but which is
best?
Linear 
Classifiers
x f yest
f(x,w,b) = sign(w x + b)
denotes +1
denotes -1

How would you

classify this data?

Misclassified
to +1 class
Classifier 
Margin
x f yest
f(x,w,b) = sign(w x + b)
denotes +1
denotes -1 Define the margin
of a linear
classifier as the
width that the
boundary could be
increased by
before hitting a
datapoint.
 Maximum 
Margin
x f yest
1. Maximizing the margin is good
accordingf(x,w,b)
to intuition and PAC
= sign(w theory
x+ b)
denotes +1 2. Implies that only support vectors are
denotes -1 important; other The
training examples
maximum
are ignorable.
margin linear
classifier
3. Empirically it works iswell.
very very the
linear classifier
Support Vectors with the, um,
are those
datapoints that maximum margin.
the margin
This is the
pushes up
against simplest kind of
SVM (Called an
LSVM)
Linear SVM
Linear SVM Mathematically
1”
= +
ss x+ M=Margin Width
l a
i c t C one
r ed z
“ P
X- -1”
b =1 s =
+ la s
wx =0 C
+b
d i c zone
t
wx 1 e
+ b =- “Pr
wx

What we know:  
(x  x )  w 2
 w . x+ + b = +1 M  
 w . x- + b = -1
w w
 w . (x+-x-) = 2
 Linear SVM Mathematically
 Goal: 1) Correctly classify all training data
if yi = +1
wxifi y= -1b  1
i

wxi  b  1
for all i
2) Maximize the Margin

yi ( wxi  b)  1
same as minimize
2
 Mandb
We can formulate a Quadratic Optimization Problem and solve for w

1 w
t
 Minimize ww
2
subject to

1 t
 ( w)  w w
2
yi ( wxi  b)  1 i
Solving the Optimization
Problem
Find w and b such that
Φ(w) =½ wTw is minimized;
and for all {(xi ,yi)}: yi (wTxi + b) ≥ 1
 Need to optimize a quadratic function subject to linear constrai
nts.
 Quadratic optimization problems are a well-known class of mat
hematical programming problems, and many (rather intricate) a
lgorithms exist for solving them.
 The solution involves constructing a dual problem where a Lag
range multiplier αi is associated with every constraint in the pri
mary problem:
Find α1…αN such that
Q(α) =Σαi - ½ΣΣαiαjyiyjxiTxj is maximized and
(1) Σαiyi = 0
(2) αi ≥ 0 for all αi
The Optimization Problem
Solution
 The solution has the form:
w =Σαiyixi b= yk- wTxk for any xk such that αk 0
 Each non-zero αi indicates that corresponding xi is a suppo
rt vector.
 Then the classifying function will have the form:
f(x) = ΣαiyixiTx + b
 Notice that it relies on an inner product between the test po
int x and the support vectors xi – we will return to this later.
 Also keep in mind that solving the optimization problem inv
olved computing the inner products xiTxj between all pairs o
f training points.
Dataset with noise

denotes +1  Hard Margin: So far we require

all data points be classified correctly
denotes -1
- No training error
 What if the training set is
noisy?
- Solution 1: use very powerful
kernels

OVERFITTING!
Soft Margin Classification
Slack variables ξi can be added to allow misclass
ification of difficult or noisy examples.

What should our quadratic

11 optimization criterion be?
2 Minimize
R
1
wx
+ b=
1
7 w.w  C  εk
+ b=
0
w x b =- 1
+
2 k 1
wx
Hard Margin v.s. Soft Margin
 The old formulation:
Find w and b such that
Φ(w) =½ wTw is minimized and for all {(xi ,yi)}
yi (wTxi + b) ≥ 1

 The new formulation incorporating slack variables:

Find w and b such that

Φ(w) =½ wTw + CΣξi is minimized and for all {(xi ,yi)}
yi (wTxi + b) ≥ 1- ξi and ξi ≥ 0 for all i

 Parameter C can be viewed as a way to control overfi

tting.
Linear SVMs: Overview
 The classifier is a separating hyperplane.
 Most “important” training points are support vectors; they defi
ne the hyperplane.
 Quadratic optimization algorithms can identify which training p
oints xi are support vectors with non-zero Lagrangian multiplier
s αi.
 Both in the dual formulation of the problem and in the solution
training points appear only inside dot products:
Find α1…αN such that
Q(α) =Σαi - ½ΣΣαiαjyiyjxiTxj is maximized and
(1) Σαiyi = 0
(2) 0 ≤ αi ≤ C for all αi

f(x) = ΣαiyixiTx + b
Non-linear SVMs
 Datasets that are linearly separable with some noise
work out great:
0 x

 But what are we going to do if the dataset is just too

hard? x
0

 How about… mapping data to a higher-dimensional

space: x2

0 x
Non-linear SVMs: Feature sp
aces
 General idea: the original input space can always be
mapped to some higher-dimensional feature space
where the training set is separable:

Φ: x → φ(x)
The “Kernel Trick”
 The linear classifier relies on dot product between vectors K(xi,xj)=xiTxj
 If every data point is mapped into high-dimensional space via some transfor
mation Φ: x → φ(x), the dot product becomes:
K(xi,xj)= φ(xi) Tφ(xj)
 A kernel function is some function that corresponds to an inner product in so
me expanded feature space.
 Example:
2-dimensional vectors x=[x1 x2]; let K(xi,xj)=(1 + xiTxj)2,
Need to show that K(xi,xj)= φ(xi) Tφ(xj):
K(xi,xj)=(1 + xiTxj)2,
= 1+ xi12xj12 + 2 xi1xj1 xi2xj2+ xi22xj22 + 2xi1xj1 + 2xi2xj2
= [1 xi12 √2 xi1xi2 xi22 √2xi1 √2xi2]T [1 xj12 √2 xj1xj2 xj22 √2xj1 √2xj2]
= φ(xi) Tφ(xj), where φ(x) = [1 x12 √2 x1x2 x22 √2x1 √2x2]
What Functions are
Kernels?
 For some functions K(xi,xj) checking that
K(xi,xj)= φ(xi) Tφ(xj) can be cumbersome.
 Mercer’s theorem:
Every semi-positive definite symmetric function is a kernel
 Semi-positive definite symmetric functions correspond to a
semi-positive definite symmetric Gram matrix:

K(x1,x1) K(x1,x2) K(x1,x3) … K(x1,xN)

K= K(x2,x1) K(x2,x2) K(x2,x3) K(x2,xN)

… … … … …
K(xN,x1) K(xN,x2) K(xN,x3) … K(xN,xN)
Examples of Kernel
Functions
 Linear: K(xi,xj)= xi Txj

 Polynomial of power p: K(xi,xj)= (1+ xi Txj)p

 Gaussian (radial-basis function network):

2
xi  x j
K (x i , x j )  exp( )
2 2

 Sigmoid: K(xi,xj)= tanh(β0xi Txj + β1)

Non-linear SVMs Mathematical
ly
 Dual problem formulation:
Find α1…αN such that
Q(α) =Σαi - ½ΣΣαiαjyiyjK(xi, xj) is maximized and
(1) Σαiyi = 0
(2) αi ≥ 0 for all αi

 The solution is:

f(x) = ΣαiyiK(xi, xj)+ b

 Optimization techniques for finding αi’s remain the same!

Nonlinear SVM - Overview
 SVM locates a separating hyperplane in the
feature space and classify points in that spa
ce
 It does not need to represent the space expl
icitly, simply by defining a kernel function
 The kernel function plays the role of the dot
product in the feature space.
Properties of SVM
 Flexibility in choosing a similarity function
 Sparseness of solution when dealing with large data
sets
- only support vectors are used to specify the separating hyperp
lane
 Ability to handle large feature spaces
- complexity does not depend on the dimensionality of the featu
re space
 Overfitting can be controlled by soft margin approac
h
 Nice math property: a simple convex optimization problem
which is guaranteed to converge to a single global solution
 Feature Selection
SVM Applications

 SVM has been used successfully in many

real-world problems
- text (and hypertext) categorization
- image classification
- bioinformatics (Protein classification,
Cancer classification)
- hand-written character recognition
 Application 1: Cancer
Classification
 High Dimensional
Genes
- p>1000; n<100 Patients g-1 g-2 …… g-p
P-1
 Imbalanced p-2
…….
- less positive samples
p-n
n
K [ x , x ]  k ( x, x )  
N
FEATURE SELECTION
 Many irrelevant features
 Noisy In the linear case,
wi2 gives the ranking of dim i
SVM is sensitive to noisy (mis-labeled) data 
Weakness of SVM
 It is sensitive to noise
- A relatively small number of mislabeled examples can dramati
cally decrease the performance

 It only considers two classes

- how to do multi-class classification with SVM?
- Answer:
1) with output arity m, learn m SVM’s
 SVM 1 learns “Output==1” vs “Output != 1”

 SVM 2 learns “Output==2” vs “Output != 2”

 :

 SVM m learns “Output==m” vs “Output != m”

2)To predict the output for a new input, just predict with each S
VM and find out which one puts the prediction the furthest into
the positive region.
Application 2: Text
Categorization
 Task: The classification of natural text (or
hypertext) documents into a fixed number of
predefined categories based on their content.
- email filtering, web searching, sorting documents by
topic, etc..
 A document can be assigned to more than
one category, so this can be viewed as a
series of binary classification problems, one
for each category
 Representation of Text
IR’s vector space model (aka bag-of-words representation)
 A doc is represented by a vector indexed by a pre-fixed

set or dictionary of terms

 Values of an entry can be binary or weights

 Normalization, stop words, word stems

 Doc x => φ(x)
Text Categorization using
SVM
 The distance between two documents is φ(x)·φ(z)

 K(x,z) = 〈 φ(x)·φ(z) is a valid kernel, SVM can be us

ed with K(x,z) for discrimination.

 Why SVM?
-High dimensional input space
-Few irrelevant features (dense concept)
-Sparse document vectors (sparse instances)
-Text categorization problems are linearly separable
Some Issues
 Choice of kernel
- Gaussian or polynomial kernel is default
- if ineffective, more elaborate kernels are needed
- domain experts can give assistance in formulating appropriate
similarity measures

 Choice of kernel parameters

- e.g. σ in Gaussian kernel
- σ is the distance between closest points with different
classifications
- In the absence of reliable criteria, applications rely on the use
of a validation set or cross-validation to set such parameters.

 Optimization criterion – Hard margin v.s. Soft margin

- a lengthy series of experiments in which various parameters ar
e tested
 Additional Resources
 An excellent tutorial on VC-dimension and Support Vec
tor Machines:
C.J.C. Burges. A tutorial on support vector machines for pattern re
cognition. Data Mining and Knowledge Discovery, 2(2):955-974,
1998.

 The VC/SRM/SVM Bible:

Statistical Learning Theory by Vladimir Vapnik, Wiley-Interscience
; 1998

http://www.kernel-machines.org/
Reference
 Support Vector Machine Classification of Microa
rray Gene Expression Data, Michael P. S. Brown
William Noble Grundy, David Lin, Nello Cristianini, C
harles Sugnet, Manuel Ares, Jr., David Haussler
 www.cs.utexas.edu/users/mooney/cs391L/svm.ppt
 Text categorization with Support Vector Machine
s:
learning with many relevant features
T. Joachims, ECML - 98