Presentation is loading. Please wait.

Presentation is loading. Please wait.

Computational Learning Theory

Similar presentations


Presentation on theme: "Computational Learning Theory"— Presentation transcript:

1 Computational Learning Theory
CS 9633 Machine Learning Computational Learning Theory Adapted from notes by Tom Mitchell

2 Theoretical Characterization of Learning Problems
Under what conditions is successful learning possible and impossible? Under what conditions is a particular learning algorithm assured of learning successfully?

3 Two Frameworks PAC (Probably Approximately Correct) Learning Framework: Identify classes of hypotheses that can and cannot be learned from a polynomial number of training examples Define a natural measure of complexity for hypothesis spaces that allows bounding the number of training examples needed Mistake Bound Framework

4 Theoretical Questions of Interest
Is it possible to identify classes of learning problems that are inherently difficult or easy, independent of the learning algorithm? Can one characterize the number of training examples necessary or sufficient to assure successful learning? How is the number of examples affected If observing a random sample of training data? if the learner is allowed to pose queries to the trainer? Can one characterize the number of mistakes that a learner will make before learning the target function? Can one characterize the inherent computational complexity of a class of learning algorithms?

5 Computational Learning Theory
Relatively recent field Area of intense research Partial answers to some questions on previous page is yes. Will generally focus on certain types of learning problems.

6 Inductive Learning of Target Function
What we are given Hypothesis space Training examples What we want to know How many training examples are sufficient to successfully learn the target function? How many mistakes will the learner make before succeeding?

7 Questions for Broad Classes of Learning Algorithms
Sample complexity How many training examples do we need to converge to a successful hypothesis with a high probability? Computational complexity How much computational effort is needed to converge to a successful hypothesis with a high probability? Mistake Bound How many training examples will the learner misclassify before converging to a successful hypothesis?

8 PAC Learning Probably Approximately Correct Learning Model
Will restrict discussion to learning boolean-valued concepts in noise-free data.

9 Problem Setting: Instances and Concepts
X is set of all possible instances over which target function may be defined C is set of target concepts learner is to learn Each target concept c in C is a subset of X Each target concept c in C is a boolean function c: X{0,1} c(x) = 1 if x is positive example of concept c(x) = 0 otherwise

10 Problem Setting: Distribution
Instances generated at random using some probability distribution D D may be any distribution D is generally not known to the learner D is required to be stationary (does not change over time) Training examples x are drawn at random from X according to D and presented with target value c(x) to the learner.

11 Problem Setting: Hypotheses
Learner L considers set of hypotheses H After observing a sequence of training examples of the target concept c, L must output some hypothesis h from H which is its estimate of c

12 Example Problem (Classifying Executables)
Three Classes (Malicious, Boring, Funny) Features a GUI present (yes/no) a Deletes files (yes/no) a Allocates memory (yes/no) a4 Creates new thread (yes/no) Distribution? Hypotheses?

13 Instance a1 a2 a3 a4 Class 1 Yes No B 2 3 F 4 M 5 6 7 8 9 10

14 Computer Science Department
True Error Definition: The true error (denoted errorD(h)) of hypothesis h with respect to target concept c and distribution D , is the probability that h will misclassify an instance drawn at random according to D. Computer Science Department CS 9633 Machine Learning

15 Error of h with respect to c
Instance space X - - - c + + h + - Computer Science Department CS 9633 Machine Learning

16 Computer Science Department
Key Points True error defined over entire instance space, not just training data Error depends strongly on the unknown probability distribution D The error of h with respect to c is not directly observable to the learner L—can only observe performance with respect to training data (training error) Question: How probable is it that the observed training error for h gives a misleading estimate of the true error? Computer Science Department CS 9633 Machine Learning

17 Computer Science Department
PAC Learnability Goal: characterize classes of target concepts that can be reliably learned from a reasonable number of randomly drawn training examples and using a reasonable amount of computation Unreasonable to expect perfect learning where errorD(h) = 0 Would need to provide training examples corresponding to every possible instance With random sample of training examples, there is always a non-zero probability that the training examples will be misleading Computer Science Department CS 9633 Machine Learning

18 Weaken Demand on Learner
Hypothesis error (Approximately) Will not require a zero error hypothesis Require that error is bounded by some constant , that can be made arbitrarily small  is the error parameter Error on training data (Probably) Will not require that the learner succeed on every sequence of randomly drawn training examples Require that its probability of failure is bounded by a constant, , that can be made arbitrarily small  is the confidence parameter Computer Science Department CS 9633 Machine Learning

19 Definition of PAC-Learnability
Definition: Consider a concept class C defined over a set of instances X of length n and a learner L using hypothesis space H. C is PAC-learnable by L using H if all c  C, distributions D over X,  such that 0 <  < ½ , and  such that 0 <  < ½, learner L will with probability at least (1 - ) output a hypothesis h H such that errorD(h)  , in time that is polynomial in 1/, 1/, n, and size(c). Computer Science Department CS 9633 Machine Learning

20 Requirements of Definition
L must with arbitrarily high probability (1-), out put a hypothesis having arbitrarily low error (). L’s learning must be efficient—grows polynomially in terms of Strengths of output hypothesis (1/, 1/) Inherent complexity of instance space (n) and concept class C (size(c)). Computer Science Department CS 9633 Machine Learning

21 Block Diagram of PAC Learning Model
Control Parameters ,  Training sample Hypothesis h Learning algorithm L Computer Science Department CS 9633 Machine Learning

22 Examples of second requirement
Consider executables problem where instances are conjunctions of boolean features: a1=yes  a2=no  a3=yes  a4=no Concepts are conjunctions of a subset of the features a1=yes  a3=yes  a4=yes Computer Science Department CS 9633 Machine Learning

23 Using the Concept of PAC Learning in Practice
We often want to know how many training instances we need in order to achieve a certain level of accuracy with a specified probability. If L requires some minimum processing time per training example, then for C to be PAC-learnable by L, L must learn from a polynomial number of training examples. Computer Science Department CS 9633 Machine Learning

24 Computer Science Department
Sample Complexity Sample complexity of a learning problem is the growth in the required training examples with problem size. Will determine the sample complexity for consistent learners. A learner is consistent if it outputs hypotheses which perfectly fit the training data whenever possible. All algorithms in Chapter 2 are consistent learners. Computer Science Department CS 9633 Machine Learning

25 Recall definition of VS
The version space, denoted VSH,D, with respect to hypothesis space H and training examples D, is the subset of hypotheses from H consistent with the training examples in D Computer Science Department CS 9633 Machine Learning

26 VS and PAC learning by consistent learners
Every consistent learner outputs a hypothesis belonging to the version space, regardless of the instance space X, hypothesis space H, or training data D. To bound the number of examples needed by any consistent learner, we need only to bound the number of examples needed to assure that the version space contains no unacceptable hypotheses. Computer Science Department CS 9633 Machine Learning

27 Computer Science Department
-exhausted Definition: Consider a hypothesis space H, target concept c, instance distribution D, and set of training examples D of c. The version space VSH,D is said to be -exhausted with respect to c and D, if every hypothesis h in VH,D has error less than  with respect to c and D. Computer Science Department CS 9633 Machine Learning

28 Exhausting the version space
Hypothesis Space H error = 0.2 r=0 error = 0.1 r=0.2 error = 0.3 r=0.4 VSH,D error = 0.1 r=0 error = 0.2 r=0.3 error = 0.3 r=0.2 Computer Science Department CS 9633 Machine Learning

29 Exhausting the Version Space
Only an observer who knows the identify of the target concept can determine with certainty whether the version space is -exhausted. But, we can bound the probability that the version space will be -exhausted after a given number of training examples Without knowing the identity of the target concept Without knowing the distribution from which training examples were drawn Computer Science Department CS 9633 Machine Learning

30 Computer Science Department
Theorem 7.1 Theorem 7.1 -exhausting the version space. If the hypothesis space H is finite, D is a sequence of m  1 independent randomly drawn examples of some target concept c, then for any 01, the probability that the version space VSH,D is not -exhausted (with respect to c) is less than or equal to |H|e-m Computer Science Department CS 9633 Machine Learning

31 Computer Science Department
Proof of theorem See text Computer Science Department CS 9633 Machine Learning

32 Number of Training Examples (Eq. 7.2)
Computer Science Department CS 9633 Machine Learning

33 Computer Science Department
Summary of Result Inequality on previous slide provides a general bound on the number of trianing examples sufficient for any consistent learner to successfully learn any target concept in H, for any desired values of  and . This number m of training examples is sufficient to assure that any consistent hypothesis will be probably (with probability 1-) approximately (within error ) correct. The value of m grows linearly with 1/ logarithmically with 1/ logarithmically with |H| The bound can be a substantial overestimate. Computer Science Department CS 9633 Machine Learning

34 Computer Science Department
Problem Suppose we have the instance space described for the EnjoySports problem: Sky (Sunny, Cloudy, Rainy) AirTemp (Warm, Cold) Humidity (Normal, High) Wind (Strong, Weak) Water (Warm, Cold) Forecast (Same, Change) Hypotheses can be as before (?, Warm, Normal, ?, ?, Same) (0, 0, 0, 0, 0, 0) How many training examples do we need to have an error rate of less than 10% with a probability of 95%? Computer Science Department CS 9633 Machine Learning

35 Computer Science Department
Limits of Equation 7.2 Equation 7.2 tell us how many training examples suffice to ensure (with probability (1-) that every hypothesis having 0 training error, will have a true error of at most . Problem: there may be no hypothesis that is consistent with if the concept is not in H. In this case, we want the minimum error hypothesis. Computer Science Department CS 9633 Machine Learning

36 Agnostic Learning and Inconsistent Hypotheses
An Agnostic Learner does not make the assumption that the concept is contained in the hypothesis space. We may want to consider the hypothesis with the minimum error Can derive a bound similar to the previous one: Computer Science Department CS 9633 Machine Learning

37 Concepts that are PAC-Learnable
Proofs that a type of concept is PAC-Learnable usually consist of two steps: Show that each target concept in C can be learned from a polynomial number of training examples Show that the processing time per training example is also polynomially bounded Computer Science Department CS 9633 Machine Learning

38 PAC Learnability of Conjunctions of Boolean Literals
Class C of target concepts described by conjunctions of boolean literals: GUI_Present  Opens_files Is C PAC learnable? Yes. Will prove by Showing that a polynomial # of training examples is needed to learn each concept Demonstrate an algorithm that uses polynomial time per training example Computer Science Department CS 9633 Machine Learning

39 Examples Needed to Learn Each Concept
Consider a consistent learner that uses hypothesis space H =C Compute number m of random training examples sufficient to ensure that L will, with probability (1 - ), output a hypothesis with maximum error . We will use m (1/)(ln|H|+ln(1/)) What is the size of the hypothesis space? Computer Science Department CS 9633 Machine Learning

40 Complexity Per Example
We just need to show that for some algorithm, we can spend a polynomial amount of time per training example. One way to do this is to give an algorithm. In this case, we can use Find-S as the learning algorithm. Find-S incrementally computes the most specific hypothesis consistent with each training example. Old  Tired + Old  Happy Tired Old  Tired Rich  Happy What is a bound on the time per example? Computer Science Department CS 9633 Machine Learning

41 Computer Science Department
Theorem 7.2 PAC-learnability of boolean conjunctions. The class C of conjunctions of boolean literals is PAC-learnable by the FIND-S algorithm using H=C Computer Science Department CS 9633 Machine Learning

42 Computer Science Department
Proof of Theorem 7.2 Equation 7.4 shows that the sample complexity for this concept class id polynomial in n, 1/, and 1/, and independent of size(c). To incrematally process each training example, the FIND-S algorithm requires effort linear in n and independent of 1/, 1/, and size(c). Therefore, this concept class is PAC-learnable by the FIND-S algorithm. Computer Science Department CS 9633 Machine Learning

43 Computer Science Department
Interesting Results Unbiased learners are not PAC learnable because they require an exponential number of examples. K-term Disjunctive Normal Form is not PAC learnable K-term Conjunctive Normal Form is a superset of k-DNF, but it is PAC learnable Computer Science Department CS 9633 Machine Learning

44 Sample Complexity with Infinite Hypothesis Spaces
Two drawbacks to previous result It often does not give a very tight bound on the sample complexity It only applies to finite hypothesis spaces Vapnik-Chervonekis dimension of H (VC dimension) Will give tighter bounds Applies to many infinite hypothesis spaces. Computer Science Department CS 9633 Machine Learning

45 Shattering a Set of Instances
Consider a subset of instances S from the instance space X. Every hypothesis imposes dichotomies on S {xS | h(x) = 1} {xS | h(x) = 0} Given some instance space S, there are 2|S| possible dichotomies. The ability of H to shatter a set of concepts is a measure of its capacity to represent target concepts defined over these instances. Computer Science Department CS 9633 Machine Learning

46 Shattering a Hypothesis Space
Definition: A set of instances S is shattered by hypothesis space H if and only if for every dichotomy of S there exists some hypothesis in H consistent with this dichotomy. Computer Science Department CS 9633 Machine Learning

47 Vapnik-Chervonenkis Dimension
Ability to shatter a set of instances is closely related to the inductive bias of the hypothesis space. An unbiased hypothesis space is one that shatters the instance space X. Sometimes H cannot be shattered, but a large subset of it can. Computer Science Department CS 9633 Machine Learning

48 Vapnik-Chervonenkis Dimension
Definition: The Vapnik-Chervonenkis dimension, VC(H) of hypothesis space H defined over instance space X, is the size of the largest finite subset of X shattered by H. If arbitrarily large finite sets of X can be shattered by H, then VC(H) = . Computer Science Department CS 9633 Machine Learning

49 Shattered Instance Space
Computer Science Department CS 9633 Machine Learning

50 Example 1 of VC Dimension
Instance space X is the set of real numbers X = R. H is the set of intervals on the real number line. Form of H is: a < x < b What is VC(H)? Computer Science Department CS 9633 Machine Learning

51 Shattering the real number line
-1.2 3.4 -1.2 3.4 6.7 What is VC(H)? What is |H|? Computer Science Department CS 9633 Machine Learning

52 Example 2 of VC Dimension
Set X of instances corresponding to numbers on the x,y plane H is the set of all linear decision surfaces What is VC(H)? Computer Science Department CS 9633 Machine Learning

53 Shattering the x-y plane
2 instances 3 instances VC(H) = ? |H| = ? Computer Science Department CS 9633 Machine Learning

54 Proving limits on VC dimension
If we find any set of instances of size d that can be shattered, then VC(H)  d. To show that VC(H) < d, we must show that no set of size d can be shattered. Computer Science Department CS 9633 Machine Learning

55 General result for r dimensional space
The VC dimension of linear decision surfaces in an r dimensional space is r+1. Computer Science Department CS 9633 Machine Learning

56 Example 3 of VC dimension
Set X of instances are conjunctions of exactly three boolean literals young  happy  single H is the set of hypothesis described by a conjunction of up to 3 boolean literals. What is VC(H)? Computer Science Department CS 9633 Machine Learning

57 Shattering conjunctions of literals
Approach: construct a set of instances of size 3 that can be shattered. Let instance i have positive literal li and all other literals negative. Representation of instances that are conjunctions of literals l1, l2 and l3 as bit strings: Instance1: 100 Instance2: Instance3: Construction of dichotomy: To exclude an instance, add appropriate li to the hypothesis. Extend the argument to n literals. Can VC(H) be greater than n (number of literals)? Computer Science Department CS 9633 Machine Learning

58 Sample Complexity and the VC dimension
Can derive a new bound for the number of randomly drawn training examples that suffice to probably approximately learn a target concept (how many examples do we need to -exhaust the version space with probability (1-)?) Computer Science Department CS 9633 Machine Learning

59 Computer Science Department
Comparing the Bounds Computer Science Department CS 9633 Machine Learning

60 Lower Bound on Sample Complexity
Theorem 7.3 Lower bound on sample complexity. Consider any concept class C such that VC(C)  2, any learner L, and any 0 <  < 1/8, and 0 <  < 1/100. Then there exists a distribution D and target concept in C such that if L observes fewer examples than Then with probability at least , L outputs a hypothesis h having errorD(h) > . Computer Science Department CS 9633 Machine Learning


Download ppt "Computational Learning Theory"

Similar presentations


Ads by Google