Title: Ch 3. Linear Models for Regression (1/2) Pattern Recognition and Machine Learning, C. M. Bishop, 2006.
1Ch 3. Linear Models for Regression (1/2)Pattern
Recognition and Machine Learning, C. M. Bishop,
2006.
- Previously summarized by Yung-Kyun Noh
- Modified and presented by Rhee, Je-Keun
- Biointelligence Laboratory, Seoul National
University - http//bi.snu.ac.kr/
2Contents
- 3.1 Linear Basis Function Models
- 3.1.1 Maximum likelihood and least squares
- 3.1.2 Geometry of least squares
- 3.1.3 Sequential learning
- 3.1.4 Regularized least squares
- 3.1.5 Multiple outputs
- 3.2 The Bias-Variance Decomposition
- 3.3 Bayesian Lear Regression
- 3.3.1 Parameter distribution
- 3.3.2 Predictive distribution
- 3.3.3 Equivalent kernel
3Linear Basis Function Models
- Linear regression
- Linear model
- Linearity in the parameters
- Using basis functions, allow nonlinear function
of the input vector x. - Simplify the analysis of this class of models
- Have some significant limitations
- M total number of parameters
- basis functions (
dummy basis function) - ,
4Basis Functions
- Polynomial functions
- Global functions of the input variable
- ? spline functions
- Gaussian basis functions
- Sigmoidal basis functions
- Logistic sigmoid functions
- Fourier basis ? wavelets
5Maximum Likelihood and Least Squares (1/2)
- Assumption Gaussian noise model
- zero mean Gaussian random variable with
precision (inverse variance) . ? - Result
- Conditional mean
(unimodal) - For dataset
- Likelihood (Drop the explicit x)
6Maximum Likelihood and Least Squares (2/3)
- Log-likelihood
- Maximization of the likelihood function under a
conditional Gaussian noise distribution for a
linear model is equivalent to minimizing a
sum-of-squares error function.
7Maximum Likelihood and Least Squares (3/3)
- The gradient of the log likelihood function
- Setting the gradient of log likelihood and
setting it to zero to get - where the NxM design matrix
8Bias and Precision Parameter by ML
- Some other solutions we can get by setting
derivative to zero. - Bias maximizing log likelihood
- The bias compensates for the difference between
the averages (over the training set) of the
target values and the weighted sum of the
averages of the basis function values. - Noise precision parameter maximizing log
likelihood
9Geometry of Least Squares
- If the number M of basis functions is smaller
than the number N of data points, then the M
vectors will span a linear subspace S
of dimensionality M. - jth column of
- y linear combination of
- The least-squares solution for w corresponds to
that choice of y that lies in subspace S and that
is closest to t.
10Sequential Learning
- On-line learning
- Technique of Stochastic gradient descent (or
sequential gradient descent) - For the case of sum-of-squares error function
(least-mean-square or the LMS algorithm)
11Regularized Least Squares
- Regularized least-square
- Control over-fitting
- Total error function
- Closed form solution (setting the gradient)
- This represents a simple extension of the
least-squares solution. - A more general regularizer
12General Regularizer
- In case q1 in general regularizer
- lasso in the statistical literature
- If ? is sufficiently large, some of the
coefficients wj are driven to zero. - Sparse model corresponding basis functions play
no role. - Minimizing the unregularized sum-of-squares error
s.t. the constraint
Contours of the regularization term
The lasso gives the sparse solution
13Regularization complexity
- Regularization allows complex models to be
trained on data sets of limited size without
severe over-fitting, essentially by limiting the
effective model complexity. - However, the problem of determining the optimal
model complexity is then shifted from on of
finding the appropriate number of basis functions
to one of determining a suitable value of the
regularization coefficient ?.
14Multiple Outputs
- For Kgt1 target variables
- 1. Introduce a different set of basis functions
for each component of t. - 2. Use the same set of basis functions to model
all of the components of the target vector. (W
MxK matrix of parameters) - For each variable tk,
- pseudo-inverse of
15The Bias-Variance Decomposition (1/4)
- Frequentist viewpoint of the model complexity
issue bias-variance trade-off. - Expected squared loss
- Bayesian the uncertainty in our model is
expressed through a posterior distribution over
w. - Frequentist make a point estimate of w based on
the data set D.
Arises from the intrinsic noise on the data
Dependent on the particular dataset D.
16The Bias-Variance Decomposition (2/4)
- Bias
- The extent to which the average prediction over
all data sets differs from the desired regression
function. - Variance
- The extent to which the solutions for individual
data sets vary around their average. - The extent to which the function y(xD) is
sensitive to the particular choice of data set. - Expected loss (bias)2 variance noise
17The Bias-Variance Decomposition (3/4)
- ? bias-variance trade-off
- Averaging many solutions for the complex model
(M25) is a beneficial procedure. - A weighted averaging (although with respect to
the posterior distribution of parameters, not
with respect to multiple data sets) of multiple
solutions lies at the heart of Bayesian approach.
18The Bias-Variance Decomposition (4/4)
- The average prediction
- Bias and variance
- Bias-variance decomposition is based on averages
with respect to ensembles of data sets
(frequentist perspective). We would be better off
combining them into a single large training set.
19Bayesian Linear Regression
- In the particular problem, it cannot be decided
simply by maximizing the likelihood function,
because it always leads to excessively complex
models and overfitting. - Independent hold-out data can be used to
determine model complexity, but this can be both
computationally expensive and wasteful of
valuable data. - Bayesian treatment of linear regression will
avoid the overfitting problem of maximum
likelihood, and will also lead to autoamtic
methods of determining model complexity using
training data alome.
20Parameter distribution (1/3)
- Conjugate prior of likelihood
- Posterior
- The maximum posterior weight vector
- If S0a -1I with a ? 0, the mean mN reduces to
wML given by (3.15)
21Parameter distribution (2/3)
- Consider prior
- Corresponding posterior
- Log of the posterior
- Maximization of this posterior distribution with
respect to w is equivalent to the minimization of
the sum-of squares error function with the
addition of a quadratic regularization term with
?a /ß.
22Parameter distribution (3/3)
- Other forms of prior over parameters
23Predictive Distribution (1/2)
Uncertainty associated with the parameters w. 0
if N?8
Mean of the Gaussian predictive distribution (red
line), and predictive uncertainty (shaded region)
as the number of data increases.
noise
24Predictive Distribution (2/2)
Draw samples from the posterior distribution over
w.
25Equivalent Kernel (1/2)
- If we substitue (3.53) into the expression (3.3),
we see that the predictive mean can be written in
the form - Mean of the predictive distribution at a point x.
-
Smoother matrix or equivalent kernel
Polynomial and sigmoidal basis function
26Equivalent Kernel (2/2)
- Instead of introducing a set of basis functions,
which implicitly determines an equivalent kernel,
we can instead define a localized kernel directly
and use this to make predictions for new input
vector x, given the observed training set. - This leads to a practical framework for
regression (and classification) called Gaussian
processes. - The equivalent kernel satisfies an important
property shared by kernel functions in general,
namely that it can be expressed in the form an
inner product with respect to a vector ?(x) of
nonlinear functions. - Inner product of nonlinear functions