2. Problem: PCA with some analytical skills related questions. Consider the general PCA problem: Given a matrix of data, X of size p × N (p < N), we want to find the "best" approximation (in the average norm square sense) of xi≈µ+Vqλi, where V, is a unitary px q (q< p) matrix, and λ; a q x 1 vector, where x is the ith column of X. Denote the eigenvalues of XXT by V1, V2, ... ,Vp, in descending order. (a) Explain what happens to the PCA analysis, if xk = V₁, for some k in {1,2,,N}. In other words, what happens to the approximation of X? Note that v₁ is the eigenvector of XXT that corresponds to its maximum eigenvalue. (b) Describe what happens to PCA, if eigenvalues of XX v₁ = 0, for ≥ 91, with and q₁ > q. In other words, is the accuracy of the PCA better? 91

Linear Algebra: A Modern Introduction
4th Edition
ISBN:9781285463247
Author:David Poole
Publisher:David Poole
Chapter6: Vector Spaces
Section6.2: Linear Independence, Basis, And Dimension
Problem 3AEXP
icon
Related questions
Question
2. Problem: PCA with some analytical skills related questions.
Consider the general PCA problem: Given a matrix of data, X of size p × N
(p < N), we want to find the "best" approximation (in the average norm square
sense) of xi≈µ+Vqλi, where V, is a unitary px q (q< p) matrix, and λ; a
q x 1 vector, where x is the ith column of X. Denote the eigenvalues of XXT
by V1, V2, ... ,Vp, in descending order.
(a) Explain what happens to the PCA analysis, if xk = V₁, for some k in
{1,2,,N}. In other words, what happens to the approximation of X?
Note that v₁ is the eigenvector of XXT that corresponds to its maximum
eigenvalue.
(b) Describe what happens to PCA, if eigenvalues of XX v₁ = 0, for ≥ 91,
with and q₁ > q. In other words, is the accuracy of the PCA better?
91
Transcribed Image Text:2. Problem: PCA with some analytical skills related questions. Consider the general PCA problem: Given a matrix of data, X of size p × N (p < N), we want to find the "best" approximation (in the average norm square sense) of xi≈µ+Vqλi, where V, is a unitary px q (q< p) matrix, and λ; a q x 1 vector, where x is the ith column of X. Denote the eigenvalues of XXT by V1, V2, ... ,Vp, in descending order. (a) Explain what happens to the PCA analysis, if xk = V₁, for some k in {1,2,,N}. In other words, what happens to the approximation of X? Note that v₁ is the eigenvector of XXT that corresponds to its maximum eigenvalue. (b) Describe what happens to PCA, if eigenvalues of XX v₁ = 0, for ≥ 91, with and q₁ > q. In other words, is the accuracy of the PCA better? 91
Expert Solution
steps

Step by step

Solved in 2 steps

Blurred answer
Recommended textbooks for you
Linear Algebra: A Modern Introduction
Linear Algebra: A Modern Introduction
Algebra
ISBN:
9781285463247
Author:
David Poole
Publisher:
Cengage Learning
Algebra & Trigonometry with Analytic Geometry
Algebra & Trigonometry with Analytic Geometry
Algebra
ISBN:
9781133382119
Author:
Swokowski
Publisher:
Cengage
Elementary Linear Algebra (MindTap Course List)
Elementary Linear Algebra (MindTap Course List)
Algebra
ISBN:
9781305658004
Author:
Ron Larson
Publisher:
Cengage Learning
College Algebra
College Algebra
Algebra
ISBN:
9781305115545
Author:
James Stewart, Lothar Redlin, Saleem Watson
Publisher:
Cengage Learning
Algebra and Trigonometry (MindTap Course List)
Algebra and Trigonometry (MindTap Course List)
Algebra
ISBN:
9781305071742
Author:
James Stewart, Lothar Redlin, Saleem Watson
Publisher:
Cengage Learning
Elements Of Modern Algebra
Elements Of Modern Algebra
Algebra
ISBN:
9781285463230
Author:
Gilbert, Linda, Jimmie
Publisher:
Cengage Learning,