# 0.1 Elements of statistical learning theory

 Page 1 / 1

## Three elements of statistical data analysis

• of learning from data and prediction problems.
• concentration inequalities
• uniform deviation bounds
• approximation theory
• rates of convergence
• that run in polynomial time (e.g., decision trees, wavelet methods, support vector machines).

## Learning from data

To formulate the basic learning from data problem, we must specify several basic elements: data spaces, probability measures, loss functions, andstatistical risk.

## Data spaces

Learning from data begins with a specification of two spaces:

$\mathcal{X}\equiv \text{Input}\phantom{\rule{4.pt}{0ex}}\text{Space}$
$\mathcal{Y}\equiv \text{Output}\phantom{\rule{4.pt}{0ex}}\text{Space}.$

The input space is also sometimes called the “feature space” or “signal domain.” The output space is also called the “class label space,”“outcome space,” “response space,” or “signal range.”

$\mathcal{X}={\mathbf{R}}^{d}\phantom{\rule{4pt}{0ex}}\phantom{\rule{4pt}{0ex}}\phantom{\rule{4pt}{0ex}}d\text{-dimensional}\phantom{\rule{4.pt}{0ex}}\text{Euclidean}\phantom{\rule{4.pt}{0ex}}\text{space}\phantom{\rule{4.pt}{0ex}}\text{of}\phantom{\rule{4.pt}{0ex}}\text{feature}\phantom{\rule{4.pt}{0ex}}\text{vectors''}$
$\mathcal{Y}=\left\{0,1\right\}\phantom{\rule{4pt}{0ex}}\phantom{\rule{4pt}{0ex}}\phantom{\rule{4pt}{0ex}}\text{two}\phantom{\rule{4.pt}{0ex}}\text{classes}\phantom{\rule{4.pt}{0ex}}\text{or}\phantom{\rule{4.pt}{0ex}}\text{class}\phantom{\rule{4.pt}{0ex}}\text{labels''}$
$\mathcal{X}=\mathbf{R}\phantom{\rule{4pt}{0ex}}\phantom{\rule{4pt}{0ex}}\phantom{\rule{4pt}{0ex}}\text{one-dimensional}\phantom{\rule{4.pt}{0ex}}\text{signal}\phantom{\rule{4.pt}{0ex}}\text{domain}\phantom{\rule{4.pt}{0ex}}\text{(e.g.,}\phantom{\rule{4.pt}{0ex}}\text{time-domain)}$
$\mathcal{Y}=\mathbf{R}\phantom{\rule{4pt}{0ex}}\phantom{\rule{4pt}{0ex}}\phantom{\rule{4pt}{0ex}}\text{real-valued}\phantom{\rule{4.pt}{0ex}}\text{signal}$

A classic example is estimating a signal $f$ in noise:

$Y=f\left(X\right)+W$

where $X$ is a random sample point on the real line and $W$ is a noise independent of $X$ .

## Probability measure and expectation

Define a joint probability distribution on $\mathcal{X}×\mathcal{Y}$ denoted ${P}_{X,Y}$ . Let $\left(X,Y\right)$ denote a pair of random variables distributed according to ${P}_{X,Y}$ . We will also have use for marginal and conditional distributions. Let ${P}_{X}$ denote the marginal distribution on $X$ , and let ${P}_{Y|X}$ denote the conditional distribution of $Y$ given $X$ . For any distribution $P$ , let $p$ denote its density function with respect to the corresponding dominating measure; e.g., Lebesgue measure for continuous random variables or counting measure for discrete random variables.

Define the expectation operator:

${E}_{X,Y}\left[f\left(X,Y\right)\right]\equiv \int f\left(x,y\right)d{P}_{X,Y}\left(x,y\right)=\int f\left(x,y\right){p}_{X,Y}\left(x,y\right)dxdy.$

We will also make use of corresponding marginal and conditional expectations such as ${E}_{X}$ and ${E}_{Y|X}$ .

Wherever convenient and obvious based on context, we may drop the subscripts (e.g., $E$ instead of ${E}_{X,Y}$ ) for notational ease.

## Loss functions

A loss function is a mapping

$\ell :\mathcal{Y}×\mathcal{Y}↦\mathbf{R}.$

In binary classification problems, $\mathcal{Y}=\left\{0,1\right\}$ . The $0/1$ loss function is usually used: $\ell \left({y}_{1},{y}_{2}\right)={1}_{{y}_{1}\ne {y}_{2}},$ where ${1}_{A}$ is the indicator function which takes a value of 1 if condition $A$ is true and zero otherwise. We typically will compare a true label $y$ with a prediction $\stackrel{^}{y}$ , in which case the $0/1$ loss simply counts misclassifications.

In regression or estimation problems, $\mathcal{Y}=R$ . The squared error loss function is often employed: $\ell \left({y}_{1},{y}_{2}\right)=\left({y}_{1}-{y}_{2}\right)2,$ the square of the difference between ${y}_{1}$ and ${y}_{2}$ . In application, we are interested in a true value $y$ in comparison to an estimate $\stackrel{^}{y}$ .

## Statistical risk

The basic problem in learning is to determine a mapping $f:\mathcal{X}↦\mathcal{Y}$ that takes an input $x\in \mathcal{X}$ and predicts the corresponding output $y\in \mathcal{Y}$ . The performance of a given map $f$ is measured by its expected loss or risk :

$R\left(f\right)\equiv {E}_{X,Y}\left[\ell ,\left(,f,\left(,X,\right),,,Y,\right)\right].$

The risk tells us how well, on average, the predictor $f$ performs with respect to the chosen loss function. A key quantity of interestis the mininum risk value, defined as

${R}^{*}=\underset{f}{inf}R\left(f\right)$

where the infinum is taking over all measurable functions.

## The learning problem

Suppose that $\left(X,Y\right)$ are distributed according to ${P}_{X,Y}$ ( $\left(X,Y\right)\sim {P}_{X,Y}$ for short). Our goal is to find a map so that $f\left(X\right)\approx Y$ with high probability. Ideally, we would chose $f$ to minimize the risk $R\left(f\right)=E\left[\ell \left(f\left(X\right),Y\right)\right]$ . However, in order to compute the risk (and hence optimize it) we need to know the jointdistribution ${P}_{X,Y}$ . In many problems of practical interest, the joint distribution is unknown, and minimizing the risk is notpossible.

Suppose that we have some exemplary samples from the distribution. Specifically, consider $n$ samples ${{X}_{i},{Y}_{i}}_{i=1}^{n}$ distributed independently and identically (iid) according to the otherwise unknown ${P}_{X,Y}$ . Let us call these samples training data , and denote the collection by ${D}_{n}\equiv {{X}_{i},{Y}_{i}}_{i=1}^{n}$ . Let's also define a collection of candidate mappings $\mathcal{F}$ . We will use the training data ${D}_{n}$ to pick a mapping ${f}_{n}\in \mathcal{F}$ that we hope will be a good predictor. This is sometimes called the Model Selection problem. Note that the selected model ${f}_{n}$ is a function of the training data:

${f}_{n}\left(X\right)=f\left(X;{D}_{n}\right),$

which is what the subscript $n$ in ${f}_{n}$ refers to. The risk of ${f}_{n}$ is given by

$R\left({f}_{n}\right)={E}_{X,Y}\left[\ell \left({f}_{n}\left(X\right),Y\right)\right].$

Note that since ${f}_{n}$ depends on ${D}_{n}$ in addition to a new random pair $\left(X,Y\right)$ , the risk is a random variable (i.e., a function of the training data ${D}_{n}$ ). Therefore, we are interested in the expected risk , computed over random realizations of the training data:

${E}_{{D}_{n}}\left[R\left({f}_{n}\right)\right].$

We hope that ${f}_{n}$ produces a small expected risk.

The notion of expected risk can be interpreted as follows. We would like to define an algorithm (a model selection process) that performswell on average, over any random sample of $n$ training data. The expected risk is a measure of the expected performance of thealgorithm with respect to the chosen loss function. That is, we are not gauging the risk of a particular map $f\in \mathcal{F}$ , but rather we are measuring the performance of the algorithm that takes any realizationof training data and selects an appropriate model in $\mathcal{F}$ .

This course is concerned with determining “good” model spaces $\mathcal{F}$ and useful and effective model selection algorithms.

what is the stm
is there industrial application of fullrenes. What is the method to prepare fullrene on large scale.?
Rafiq
industrial application...? mmm I think on the medical side as drug carrier, but you should go deeper on your research, I may be wrong
Damian
How we are making nano material?
what is a peer
What is meant by 'nano scale'?
What is STMs full form?
LITNING
scanning tunneling microscope
Sahil
how nano science is used for hydrophobicity
Santosh
Do u think that Graphene and Fullrene fiber can be used to make Air Plane body structure the lightest and strongest. Rafiq
Rafiq
what is differents between GO and RGO?
Mahi
what is simplest way to understand the applications of nano robots used to detect the cancer affected cell of human body.? How this robot is carried to required site of body cell.? what will be the carrier material and how can be detected that correct delivery of drug is done Rafiq
Rafiq
what is Nano technology ?
write examples of Nano molecule?
Bob
The nanotechnology is as new science, to scale nanometric
brayan
nanotechnology is the study, desing, synthesis, manipulation and application of materials and functional systems through control of matter at nanoscale
Damian
Is there any normative that regulates the use of silver nanoparticles?
what king of growth are you checking .?
Renato
What fields keep nano created devices from performing or assimulating ? Magnetic fields ? Are do they assimilate ?
why we need to study biomolecules, molecular biology in nanotechnology?
?
Kyle
yes I'm doing my masters in nanotechnology, we are being studying all these domains as well..
why?
what school?
Kyle
biomolecules are e building blocks of every organics and inorganic materials.
Joe
anyone know any internet site where one can find nanotechnology papers?
research.net
kanaga
sciencedirect big data base
Ernesto
Introduction about quantum dots in nanotechnology
what does nano mean?
nano basically means 10^(-9). nanometer is a unit to measure length.
Bharti
do you think it's worthwhile in the long term to study the effects and possibilities of nanotechnology on viral treatment?
absolutely yes
Daniel
how to know photocatalytic properties of tio2 nanoparticles...what to do now
it is a goid question and i want to know the answer as well
Maciej
Abigail
for teaching engĺish at school how nano technology help us
Anassong
How can I make nanorobot?
Lily
Do somebody tell me a best nano engineering book for beginners?
there is no specific books for beginners but there is book called principle of nanotechnology
NANO
how can I make nanorobot?
Lily
what is fullerene does it is used to make bukky balls
are you nano engineer ?
s.
fullerene is a bucky ball aka Carbon 60 molecule. It was name by the architect Fuller. He design the geodesic dome. it resembles a soccer ball.
Tarell
what is the actual application of fullerenes nowadays?
Damian
That is a great question Damian. best way to answer that question is to Google it. there are hundreds of applications for buck minister fullerenes, from medical to aerospace. you can also find plenty of research papers that will give you great detail on the potential applications of fullerenes.
Tarell
how did you get the value of 2000N.What calculations are needed to arrive at it
Privacy Information Security Software Version 1.1a
Good
Got questions? Join the online conversation and get instant answers!