Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Questions about the linear programme #1

Closed
szcf-weiya opened this issue Jun 28, 2019 · 1 comment
Closed

Questions about the linear programme #1

szcf-weiya opened this issue Jun 28, 2019 · 1 comment

Comments

@szcf-weiya
Copy link

Hi, I find the code following the link in your paper. When I read the step 1 of AdaLDA, I am curious about how can you treat step 1 as a linear programme, and now I am checking your code implementation, but I still have some questions.
It seems that you decomposed
,
then

and then you can write the following code

ADAM/AdaLDA.m

Lines 30 to 35 in fd0b125

f=ones(2*p,1);
CoeffM=[hatSigma-B -(hatSigma-B);-(hatSigma+B) hatSigma+B];
Coeffb=[a+hatdelta; a-hatdelta];
options=optimoptions('linprog','Algorithm','interior-point','Display','none');
uv=linprog(f,CoeffM,Coeffb,[],[],zeros(2*p,1),[],[],options);
beta0=uv(1:p)-uv((p+1):(2*p));

But it seems that we would have additional constraints, i.e., either or should be zero by the definition.
Maybe I have missed some other points, and wish you can help me.

@szcf-weiya
Copy link
Author

Ohhh..., I see.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant