Line 3: Line 3:
  
 
<center><font size= 5>
 
<center><font size= 5>
−
[[ECE662_Bayesian_Parameter_Estimation_S14_SF|Bayesian Parameter Estimation: Gaussian Case]]
+
[[ECE662_Bayesian_Parameter_Estimation_S14_SF|Bayesian Parameter Estimation with examples]]
 
</font size>
 
</font size>
  
−
A [https://www.projectrhea.org/learning/slectures.php slecture] by [[ECE]] student [[user:SFang | Shaobo Fang]]  
+
A [https://www.projectrhea.org/learning/slectures.php slecture] by [[ECE]] student [[user: wang1317 | Yu Wang]]  
  
 
Loosely based on the [[2014_Spring_ECE_662_Boutin|ECE662 Spring 2014 lecture]] material of [[user:mboutin|Prof. Mireille Boutin]].  
 
Loosely based on the [[2014_Spring_ECE_662_Boutin|ECE662 Spring 2014 lecture]] material of [[user:mboutin|Prof. Mireille Boutin]].  
Line 17: Line 17:
  
  
−
According to Chapter #3.3 (Duda's book), although the answers we get by BPE will generally be nearly identical to those obtained by maximum likelihood estimation, the conceptual difference is significant. For maximum likelihood estimation, the parameter <math>\theta</math> is a fixed while in Bayersian estimation <math>\theta</math> is considered to be a random variable.
+
Suppose that we have an observable random variable $\bs X$  for an experiment, that takes values in a set S. Suppose that distribution of $\bs X$  depends on a parameter $\theta$ taking values in a parameter space $\Theta$. We will denote the probability density function of $\bs X$ for a given value of $\theta$ by $f(\bs x \mid \theta)$ for $\bs x \in S$ and $\theta \in S$. Of course, our data variable X is almost always vector-valued. The parameter $\theta$ may also be vector-valued.
  
−
By definition, given samples class <math>\mathcal{D}</math>, Bayes' formula then becomes:
+
In Bayesian analysis, named for the famous Thomas Bayes, we treat the parameter $\theta$ as a random variable, with a given probability density function $h(\theta)$ for $\theta \in \Theta$. The corresponding distribution is called the prior distribution of $\theta$ and is intended to reflect our knowledge (if any) of the parameter, before we gather data. After observing $x \in S$, we then use Bayes' theorem, to compute the conditional probability density function of $\theta$ given $\bs X=\bs x$.
  
−
 
+
First recall that the joint probability density function of $(\bs X,\theta)$ is the mapping on $S \times \Theta$ given by
−
<center>
+
\[
−
<math>P(w_i|x,D) = \frac{p(x|w_i,D)P(w_i|D)}{\sum_{j = 1}^c p(x|w_j,D)P(w_j|D)}</math>
+
(\bs{x}, \theta) \mapsto h(\theta) f(\bs{x} \mid \theta)
−
</center>
+
\]
−
 
+
Next recall that the (marginal) probability density function f of $\bs X$ is given by
−
As the above equation suggests, we can use the information provided by the training data to help determine both the class-conditional densities and the priori probabilities.
+
\[
−
 
+
f(\bs{x}) = \sum_{\theta \in \Theta} h(\theta) f(\bs{x} | \theta), \quad \bs{x} \in S
−
Furthermore, since we are treating supervised case, we can separate the training samples by class into c subsets <math>\mathcal{D}_1, \mathcal{D}_2, ..., \mathcal{D}_c</math>, accordingly:
+
\]
−
 
+
if the parameter has a discrete distribution, or
−
<center>
+
\[
−
<math>P(w_i|x,D) = \frac{p(x|w_i,D_i)P(w_i)}{\sum_{j = 1}^c p(x|w_j,D_j)P(w_j)}</math>
+
f(\bs{x}) = \int_\Theta h(\theta) f(\bs{x} | \theta) \, d\theta, \quad \bs{x} \in S
−
</center>
+
\]
−
 
+
if the parameter has a continuous distribution. Finally, the conditional probability density function of $\theta$ given $\bs X= \bs x$ is
−
Now, assume <math>p(x)</math> has a parameter form. We are given a set of <math>N</math> independent samples <math>\mathcal{D} = \{x_1, x_2, ... , x_N \}</math>. View <math>\theta</math> as a random variable. Consider more specifically in continuous case:
+
\[
−
 
+
h(\theta \mid \bs{x}) = \frac{h(\theta) f(\bs{x} \mid \theta)}{f(\bs{x})}; \quad \theta \in \Theta, \; \bs{x} \in S
−
<math>p(x|D)</math> can be computed as:
+
\]
−
<center>
+
The conditional distribution of $\theta$ given $\bs X=\bs x$ is called the \textit{posterior} distribution, and is an updated distribution, given the information in the data.
−
<math>p(x|D) = \int p(x, \theta|D)d\theta = \int p(x|\theta)p(\theta|D)d\theta</math>
+
Finally, if $\theta$ is a real parameter, the conditional expected value $\mathbb{E}(\theta \mid \bs X)$ is the Bayes' estimator of $\theta$. Recall that $\mathbb{E}(\theta \mid \bs X) $is a function of X and, among all functions of X, is closest to $\theta$ in the mean square sense. Thus, once we collect the data and observe $\bs X=\bs x$, the estimate of $\theta$ is $\mathbb{E}(\theta \mid \bs X)$.
−
</center>
+
 
----
 
----
  

Revision as of 10:08, 1 May 2014


Bayesian Parameter Estimation with examples

A slecture by ECE student Yu Wang

Loosely based on the ECE662 Spring 2014 lecture material of Prof. Mireille Boutin.

Introduction: Bayesian Estimation

Suppose that we have an observable random variable $\bs X$ for an experiment, that takes values in a set S. Suppose that distribution of $\bs X$ depends on a parameter $\theta$ taking values in a parameter space $\Theta$. We will denote the probability density function of $\bs X$ for a given value of $\theta$ by $f(\bs x \mid \theta)$ for $\bs x \in S$ and $\theta \in S$. Of course, our data variable X is almost always vector-valued. The parameter $\theta$ may also be vector-valued.

In Bayesian analysis, named for the famous Thomas Bayes, we treat the parameter $\theta$ as a random variable, with a given probability density function $h(\theta)$ for $\theta \in \Theta$. The corresponding distribution is called the prior distribution of $\theta$ and is intended to reflect our knowledge (if any) of the parameter, before we gather data. After observing $x \in S$, we then use Bayes' theorem, to compute the conditional probability density function of $\theta$ given $\bs X=\bs x$.

First recall that the joint probability density function of $(\bs X,\theta)$ is the mapping on $S \times \Theta$ given by \[ (\bs{x}, \theta) \mapsto h(\theta) f(\bs{x} \mid \theta) \] Next recall that the (marginal) probability density function f of $\bs X$ is given by \[ f(\bs{x}) = \sum_{\theta \in \Theta} h(\theta) f(\bs{x} | \theta), \quad \bs{x} \in S \] if the parameter has a discrete distribution, or \[ f(\bs{x}) = \int_\Theta h(\theta) f(\bs{x} | \theta) \, d\theta, \quad \bs{x} \in S \] if the parameter has a continuous distribution. Finally, the conditional probability density function of $\theta$ given $\bs X= \bs x$ is \[ h(\theta \mid \bs{x}) = \frac{h(\theta) f(\bs{x} \mid \theta)}{f(\bs{x})}; \quad \theta \in \Theta, \; \bs{x} \in S \] The conditional distribution of $\theta$ given $\bs X=\bs x$ is called the \textit{posterior} distribution, and is an updated distribution, given the information in the data. Finally, if $\theta$ is a real parameter, the conditional expected value $\mathbb{E}(\theta \mid \bs X)$ is the Bayes' estimator of $\theta$. Recall that $\mathbb{E}(\theta \mid \bs X) $is a function of X and, among all functions of X, is closest to $\theta$ in the mean square sense. Thus, once we collect the data and observe $\bs X=\bs x$, the estimate of $\theta$ is $\mathbb{E}(\theta \mid \bs X)$.

Bayesian Parameter Estimation: General Theory

We first start with a generalized approach which can be applied to any situation in which the unknown density can be parameterized. The basic assumptions are as follows:

1. The form of the density $ p(x|\theta) $ is assumed to be known, but the value of the parameter vector $ \theta $ is not known exactly.

2. The initial knowledge about $ \theta $ is assumed to be contained in a known a priori density $ p(\theta) $.

3. The rest of the knowledge about $ \theta $ is contained in a set $ \mathcal{D} $ of n samples $ x_1, x_2, ... , x_n $ drawn independently according to the unknown probability density $ p(x) $.

Accordingly, already know:

$ p(x|D) = \int p(x|\theta)p(\theta|D)d\theta $

and By Bayes Theorem,

$ p(\theta|D) = \frac{p(D|\theta)p(\theta)}{\int p(D|\theta)p(\theta|D)d\theta} $


Now, since we are attempting to transform the equation to be based on samples $ x_k $, by independent assumption,

$ p(D|\theta) = \prod_{k = 1}^n p(x_k|\theta) $

Hence, if a sample $ \mathcal{D} $ has n samples, we can denote the sample space as: $ \mathcal{D}^n = \{x_1, x_2, ... x_n\} $.

Combine the sample space definition with the equation above:


$ p(D^n|\theta) = p(D^{n-1}|\theta)p(x_n|\theta) $

Using this equation, we can transform the Bayesian Parameter Estimation to:

$ p(\theta|D^n) = \frac{p(x_n|\theta)p(\theta|D^{n-1})}{\int p(x_n|\theta)p(\theta|D^{n-1})d\theta} $



Bayesian Parameter Estimation: Gaussian Case

The Univariate Case: $ p(\mu|\mathcal{D}) $

Consider the case where $ \mu $ is the only unknown parameter. For simplicity we assume:

$ p(x|\mu) \sim N(\mu, \sigma^2) $
and
$ p(\mu) \sim N(\mu_0, \sigma_0^2) $

From the previous section, the following expression could be easily obtained using Bayes' formula:

$ p(\mu|D) = \alpha \prod_{k = 1}^n p(x_k|\mu)p(\mu) $

Where $ \alpha $ is a factorization factor independent of $ \mu $.

Now, substitute $ p(x_k|\mu) $ and $ p(u) $ with:

$ p(x_k|\mu) = \frac{1}{(2\pi\sigma^2)^{1/2}}exp[-\frac{1}{2}(\frac{x_k-\mu}{\sigma})^{2}] $
$ p(u) = \frac{1}{(2\pi\sigma_0^2)^{1/2}}exp[-\frac{1}{2}(\frac{\mu-\mu_0}{\sigma_0})^{2}] $

The equation has now become:

$ p(\mu|D) = \alpha \prod_{k = 1}^n \frac{1}{(2\pi\sigma^2)^{1/2}}exp[-\frac{1}{2}(\frac{x_k-\mu}{\sigma})^{2}] \frac{1}{(2\pi\sigma_0^2)^{1/2}}exp[-\frac{1}{2}(\frac{\mu-\mu_0}{\sigma_0})^{2}] $
$ p(\mu|D) = \alpha \prod_{k = 1}^n \frac{1}{(2\pi\sigma^2)^{1/2}} \frac{1}{(2\pi\sigma_0^2)^{1/2}}exp[-\frac{1}{2}(\frac{\mu-\mu_0}{\sigma_0})^{2} -\frac{1}{2}(\frac{x_k-\mu}{\sigma})^{2}] $

Update the scaling factor to $ \alpha' $ and $ \alpha'' $ correspondingly,

$ p(\mu|D) = \alpha' exp \sum_{k=1}^n(-\frac{1}{2}(\frac{\mu-\mu_0}{\sigma_0})^{2} -\frac{1}{2}(\frac{x_k-\mu}{\sigma})^{2}) $
$ p(\mu|D) = \alpha'' exp [-\frac{1}{2}(\frac{n}{\sigma^2} + \frac{1}{\sigma_0^2})\mu^2 -2(\frac{1}{\sigma^2}\sum_{k=1}^nx_k + \frac{\mu_0}{\sigma_0^2})\mu] $

With the knowledge of Gaussian distribution:

$ p(u|D) = \frac{1}{(2\pi\sigma_n^2)^{1/2}}exp[-\frac{1}{2}(\frac{\mu-\mu_n}{\sigma_n})^{2}] $

Finally, the estimate of $ u_n $ can be obtained:

$ \mu_n = (\frac{n\sigma_0^2}{n\sigma_0^2 + \sigma^2})\bar{x_n} + \frac{\sigma^2}{n\sigma_0^2 + \sigma^2}\mu_0 $

Where $ \bar{x_n} $ is defined as sample means and $ n $ is the sample size.

In order to form a Gaussian distribution, the variance $ \sigma_n^2 $ associated with $ \mu_n $ could also be obtained correspondingly as:

$ \sigma_n^2 = \frac{\sigma_0^2 \sigma^2}{n\sigma_0^2 + \sigma^2} $


Observation:

With $ N \to \infty $,
$ \sigma_D \to 0 $

$ p(\mu|D) $ becomes more sharply peaked around $ \mu_D $

The Univariate Case: $ p(x|\mathcal{D}) $

Having obtained the posteriori density for the mean $ u_n $ of set $ \mathcal{D} $, the remaining of the task is to estimate the "class-conditional" density for $ p(x|D) $.

Based on the text Duda's chatpter #3.4.2 and Prof. Mimi's notes:


$ p(x|\mathcal{D}) = \int p(x|\mu)p(\mu|\mathcal{D})d\mu $
$ p(x|\mathcal{D}) = \int \frac{1}{\sqrt{2 \pi } \sigma} \exp[{-\frac{1}{2} (\frac{x-\mu}{\sigma})^2}] \frac{1}{\sqrt{2 \pi } \sigma_n} \exp[{-\frac{1}{2} (\frac{\mu-\mu_n}{\sigma_n})^2}] d\mu $


$ p(x|\mathcal{D}) = \frac{1}{2\pi\sigma\sigma_n} exp [-\frac{1}{2} \frac{(x-\mu)}{\sigma^2 + \sigma_n^2}]f(\sigma,\sigma_n) $


Where $ f(\sigma, \sigma_n) $ is defined as:


$ f(\sigma,\sigma_n) = \int exp[-\frac{1}{2}\frac{\sigma^2 + \sigma_n^2}{\sigma^2 \sigma_n ^2}(\mu - \frac{\sigma_n^2 x+\sigma^2 \mu_n}{\sigma^2+\sigma_n^2})^2]d\mu $

Hence, $ p(x|D) $ is normally distributed as:

$ p(x|D) \sim N(\mu_n, \sigma^2 + \sigma_n^2) $

References

[1]. Mireille Boutin, "ECE662: Statistical Pattern Recognition and Decision Making Processes," Purdue University, Spring 2014.

[2]. R. Duda, P. Hart, Pattern Classification. Wiley-Interscience. Second Edition, 2000.

Questions and comments

If you have any questions, comments, etc. please post them on this page.

Back to ECE662, Spring 2014

Retrieved from "https://www.projectrhea.org/rhea/index.php?title=Bayes_Parameter_Estimation_with_examples&oldid=64902"
Shortcuts
Help Main Wiki Page Random Page Special Pages Log in
Search

Alumni Liaison

ECE462 Survivor

Seraj Dosenbach