Reputation
1,872
Next privilege 2,000 Rep.
Edit questions and answers
Badges
1 10 33
Impact
~67k people reached

May
15
comment Why does $\frac{\textbf{g}^T\textbf{d}}{\textbf{d}^T\textbf{H}\textbf{d}}$ give the maximum of function $\mathcal{D}(\textbf{x}+\lambda\textbf{d})$
Thank you :) Appreciate it
May
15
comment Why does $\frac{\textbf{g}^T\textbf{d}}{\textbf{d}^T\textbf{H}\textbf{d}}$ give the maximum of function $\mathcal{D}(\textbf{x}+\lambda\textbf{d})$
Thank you, the reference material is in my post if you want to see it :)
May
15
comment Why does $\frac{\textbf{g}^T\textbf{d}}{\textbf{d}^T\textbf{H}\textbf{d}}$ give the maximum of function $\mathcal{D}(\textbf{x}+\lambda\textbf{d})$
Thank you very much =)
May
15
accepted Why does $\frac{\textbf{g}^T\textbf{d}}{\textbf{d}^T\textbf{H}\textbf{d}}$ give the maximum of function $\mathcal{D}(\textbf{x}+\lambda\textbf{d})$
May
14
revised Why does $\frac{\textbf{g}^T\textbf{d}}{\textbf{d}^T\textbf{H}\textbf{d}}$ give the maximum of function $\mathcal{D}(\textbf{x}+\lambda\textbf{d})$
edited body
May
14
comment Why does $\frac{\textbf{g}^T\textbf{d}}{\textbf{d}^T\textbf{H}\textbf{d}}$ give the maximum of function $\mathcal{D}(\textbf{x}+\lambda\textbf{d})$
Okay, sorry about that. What do you want me to do? I'm not sure what you meant exactly :) P.S. I changed the question back to the way it was before you commented :) Thank you
May
14
comment Why does $\frac{\textbf{g}^T\textbf{d}}{\textbf{d}^T\textbf{H}\textbf{d}}$ give the maximum of function $\mathcal{D}(\textbf{x}+\lambda\textbf{d})$
Roger that @S.B. :) It wasn't so hard after all x) Thank you, P.S. if you want to post your comment as answer I can accept it.
May
14
revised Why does $\frac{\textbf{g}^T\textbf{d}}{\textbf{d}^T\textbf{H}\textbf{d}}$ give the maximum of function $\mathcal{D}(\textbf{x}+\lambda\textbf{d})$
edited body
May
14
comment Why does $\frac{\textbf{g}^T\textbf{d}}{\textbf{d}^T\textbf{H}\textbf{d}}$ give the maximum of function $\mathcal{D}(\textbf{x}+\lambda\textbf{d})$
Aah okay, so the equation follows simply by taking the derivative of $\mathcal{D}$ w.r.t $\lambda$ and equating to zero? In the unconstrained case I mean :)
May
14
revised Why does $\frac{\textbf{g}^T\textbf{d}}{\textbf{d}^T\textbf{H}\textbf{d}}$ give the maximum of function $\mathcal{D}(\textbf{x}+\lambda\textbf{d})$
added 80 characters in body
May
14
asked Why does $\frac{\textbf{g}^T\textbf{d}}{\textbf{d}^T\textbf{H}\textbf{d}}$ give the maximum of function $\mathcal{D}(\textbf{x}+\lambda\textbf{d})$
May
14
awarded  Popular Question
May
12
accepted How to project gradient vector to subspace defined by linear constraints
May
12
comment Constructing canonical tableau for a linear programming problem involving SVM
Thank you very much =)
May
12
accepted Constructing canonical tableau for a linear programming problem involving SVM
May
11
comment How to project gradient vector to subspace defined by linear constraints
Thank you very much! =) I will look into the literature you provided and the solution you presented here :) Appreciate it!
May
11
comment How to project gradient vector to subspace defined by linear constraints
Thank you =) appreciate it
May
11
comment How to project gradient vector to subspace defined by linear constraints
Thank you very much :) I'll look into it :)
May
11
comment How to project gradient vector to subspace defined by linear constraints
..and HOW it is implemented. Basically I want to make a tutorial for a beginner student about SVM on 1) What SVM is and 2) How to implement and optimize it. I want to include everything from explanation to actual implementation without the usage of any packages. So that the reader himself can code SVM from beginning to end.
May
11
comment How to project gradient vector to subspace defined by linear constraints
Hi @littleO no, this is for my own curiosity :) I'm studying about the learning method Support Vector Machines (SVM) and while I've been studying it I have noticed that there are no good examples on the web or sources on how to actually implement it from beginning to the end. I hate it when I read the materials they always say: "this is what SVM is AND for solving the parameters we use A PACKAGE" so it's like a black box what I'm using :( and I really want to know what's happening under the hood. Like if I'm a new student and I want to understand how SVM works I want to understand what SVM is.