SLIDE 1
Introduction to Machine Learning CMU-10701
- 8. Stochastic Convergence
Barnabás Póczos
Motivation
2
Introduction to Machine Learning CMU-10701 8. Stochastic - - PowerPoint PPT Presentation
Introduction to Machine Learning CMU-10701 8. Stochastic - - PowerPoint PPT Presentation
Introduction to Machine Learning CMU-10701 8. Stochastic Convergence Barnabs Pczos Motivation 2 What have we seen so far? Several algorithms that seem to work fine on training datasets: Linear regression Nave Bayes classifier
SLIDE 2
SLIDE 3
What have we seen so far?
3
Several algorithms that seem to work fine on training datasets:
- Linear regression
- Naïve Bayes classifier
- Perceptron classifier
- Support Vector Machines for regression and classification
How good are these algorithms on unknown test sets? How many training samples do we need to achieve small error? What is the smallest possible error we can achieve?
) Learning Theory
To answer these questions, we will need a few powerful tools
SLIDE 4
Basic Estimation Theory
4
SLIDE 5
Rolling a Dice, Estimation of parameters θ1,θ2,…,θ6
24 120 60 12
5
Does the MLE estimation converge to the right value? How fast does it converge?
SLIDE 6
6
Rolling a Dice Calculating the Empirical Average
Does the empirical average converge to the true mean? How fast does it converge?
SLIDE 7
5 sample traces
7
How fast do they converge?
Rolling a Dice, Calculating the Empirical Average
SLIDE 8
Key Questions
I want to know the coin parameter θ2[0,1] within ε = 0.1 error, with probability at least 1-δ = 0.95.
How many flips do I need?
8
- Do empirical averages converge?
- Does the MLE converge in the dice rolling problem?
- What do we mean on convergence?
- What is the rate of convergence?
Applications:
- drug testing (Does this drug modifies the average blood pressure?)
- user interface design (We will see later)
SLIDE 9
Outline
Theory:
- Stochastic Convergences:
– Weak convergence = Convergence in distribution – Convergence in probability – Strong (almost surely) – Convergence in Lp norm
9
- Limit theorems:
– Law of large numbers – Central limit theorem
- Tail bounds:
– Markov, Chebyshev
SLIDE 10
Stochastic convergence definitions and properties
10
SLIDE 11
Convergence of vectors
11
SLIDE 12
Convergence in Distribution = Convergence Weakly = Convergence in Law
12
Notation:
Let {Z, Z1, Z2, …} be a sequence of random variables.
Definition: This is the “weakest” convergence.
SLIDE 13
Only the distribution functions converge! (NOT the values of the random variables)
1 a
13
Convergence in Distribution = Convergence Weakly = Convergence in Law
SLIDE 14
14
Continuity is important!
Proof: The limit random variable is constant 0: Example:
In this example the limit Z is discrete, not random (constant 0), although Zn is a continuous random variable. 1 1/n 1
Convergence in Distribution = Convergence Weakly = Convergence in Law
SLIDE 15 This image cannot currently be displayed.
15
Properties
Scheffe's theorem:
convergence of the probability density functions ) convergence in distribution
Example:
(Central Limit Theorem)
Zn and Z can still be independent even if their distributions are the same!
Convergence in Distribution = Convergence Weakly = Convergence in Law
SLIDE 16
Convergence in Probability
16
Notation: Definition:
This indeed measures how far the values of Zn(ω) and Z(ω) are from each other.
SLIDE 17
Almost Surely Convergence
17
Notation: Definition:
SLIDE 18
Convergence in p-th mean, Lp norm
Definition:
18
Notation: Properties:
SLIDE 19
Counter Examples
19
SLIDE 20
Further Readings on Stochastic convergence
- http://en.wikipedia.org/wiki/Convergence_of_random_variables
- Patrick Billingsley: Probability and Measure
- Patrick Billingsley: Convergence of Probability Measures
20
SLIDE 21
Finite sample tail bounds
Useful tools!
21
SLIDE 22 This image cannot currently be displayed.
Gauss Markov inequality
Decompose the expectation
If X is any nonnegative random variable and a > 0, then
Proof: Corollary: Chebyshev's inequality
22
SLIDE 23
Chebyshev inequality
If X is any nonnegative random variable and a > 0, then
Proof: Here Var(X) is the variance of X, defined as:
23
SLIDE 24 This image cannot currently be displayed.
Generalizations of Chebyshev's inequality
Chebyshev:
Asymmetric two-sided case (X is asymmetric distribution) Symmetric two-sided case (X is symmetric distribution) This is equivalent to this: There are lots of other generalizations, for example multivariate X.
24
SLIDE 25
Higher moments?
Chebyshev: Markov: Higher moments:
where n ≥ 1
Other functions instead of polynomials? Exp function: Proof:
(Markov ineq.)
25
SLIDE 26
Law of Large Numbers
26
SLIDE 27
Do empirical averages converge?
27
Answer: Yes, they do. (Law of large numbers)
Chebyshev’s inequality is good enough to study the question:
Do the empirical averages converge to the true mean?
SLIDE 28
Law of Large Numbers
28
Strong Law of Large Numbers: Weak Law of Large Numbers:
SLIDE 29
Weak Law of Large Numbers
Proof I:
Assume finite variance. (Not very important) Therefore, As n approaches infinity, this expression approaches 1.
29
SLIDE 30
What we have learned today
30
Theory:
- Stochastic Convergences:
– Weak convergence = Convergence in distribution – Convergence in probability – Strong (almost surely) – Convergence in Lp norm
- Limit theorems:
– Law of large numbers – Central limit theorem
- Tail bounds:
– Markov, Chebyshev
SLIDE 31
Thanks for your attention
31