Proving diagonal entries of R in QR decomposition nonzero

In summary, the property of the inner product mentioned in the original post can be derived from the properties of the inner product and scalar multiplication. It states that if u = v, then <u, w> = 0, and can be extended to any scalar multiple of v.
  • #1
derryck1234
56
0

Homework Statement



Prove that the diagonal entries of R in the QR decomposition are non-zero.

Homework Equations



ui = qi + <ui, q1>q1 + <ui, q2>q2 + ... + <ui, qi-1>qi-1 => From the general equation for the Gram-Schmidt process.

<ui, qi> => From the diagonal entries of QR.

The Attempt at a Solution



I have the solution from another website. I just want help regarding the part where the properties of the inner product are used in the following step:

<qi + <ui, q1>q1 + <ui, q2>q2 ... + <ui, qi-1>qi-1, qi>

to

<qi, qi> + <ui, q1><q1, qi> + ... + <ui, qi-1><qi-1, qi>

I have not seen a property of the inner product specifying that:

<<u, v>v,w> = <u,v><v,w>

Or, have I written it correctly?

Please help.

Thanks
 
Physics news on Phys.org
  • #2




Hello,

You are correct in saying that the property you mentioned is not a direct property of the inner product. However, it can be derived from the properties of the inner product and the properties of scalar multiplication. Here is the proof for your reference:

Let u, v, and w be vectors and c be a scalar. Then, we have:

<u + cv, w> = <u, w> + c<v, w> [Property of the inner product]

Now, let u = v in the above equation. Then, we get:

<2v, w> = <v, w> + 2<v, w> [Substituting u = v]

<2v, w> = 3<v, w> [Simplifying]

<2v, w> = 3<v, w> [Distributing the scalar multiplication]

2<v, w> = 3<v, w> [Dividing both sides by 2]

<v, w> = 0 [Subtracting 2<v, w> from both sides]

Therefore, we can see that if u = v, then <u, w> = 0, which is the property you mentioned. This can be extended to any scalar multiple of v, including <ui, qi-1>, where i = 1, 2, ..., n.

I hope this helps! Let me know if you have any further questions.
 

1. How is the QR decomposition used to prove the diagonal entries of R are nonzero?

The QR decomposition is a matrix factorization method used to express a matrix as the product of an orthogonal matrix (Q) and an upper triangular matrix (R). By examining the diagonal entries of R, we can determine if they are all nonzero, which is a necessary condition for the QR decomposition to be valid.

2. What is the significance of proving that the diagonal entries of R in QR decomposition are nonzero?

Showing that the diagonal entries of R are nonzero ensures that the QR decomposition is well-defined and unique. It also allows for efficient computation of the QR decomposition, as the diagonal entries can be used to solve linear systems of equations.

3. Can the diagonal entries of R be zero in certain cases?

Yes, the diagonal entries of R can be zero in cases where the matrix being decomposed has repeated columns. This is known as rank deficiency and can lead to a non-unique QR decomposition.

4. How does the QR decomposition help with solving linear systems of equations?

The QR decomposition allows us to express a matrix as the product of two triangular matrices, which simplifies the process of solving linear systems of equations. The diagonal entries of R can be used to easily solve these systems, making the QR decomposition an efficient method for solving linear equations.

5. Are there other methods for proving the diagonal entries of R are nonzero?

Yes, there are other methods such as using the Gram-Schmidt process or the Householder transformation to compute the QR decomposition. However, the QR decomposition is considered to be the most efficient and accurate method for proving the diagonal entries of R are nonzero.

Similar threads

  • Calculus and Beyond Homework Help
Replies
1
Views
1K
  • Calculus and Beyond Homework Help
Replies
2
Views
1K
  • Linear and Abstract Algebra
Replies
1
Views
1K
  • Calculus and Beyond Homework Help
Replies
4
Views
1K
  • Introductory Physics Homework Help
Replies
1
Views
1K
  • Calculus and Beyond Homework Help
Replies
5
Views
1K
  • Calculus and Beyond Homework Help
Replies
1
Views
3K
  • Linear and Abstract Algebra
Replies
2
Views
608
  • MATLAB, Maple, Mathematica, LaTeX
Replies
1
Views
2K
  • Advanced Physics Homework Help
Replies
4
Views
5K
Back
Top