I'm going to assume that near-duplicate columns happen neatly and that only complete near-duplicate columns count
A = [1 1.2 3 3.1;
1 1.3 3 3.2;
2 2.1 4 4.1]
% pick some tolerance
tol=0.5;
goodcols=find([1 any(abs(diff(A,1,2))>=tol,1)]);
Agood=A(:,goodcols)
gives us:
Agood =
1 3
1 3
2 4
Of course, this doesn't account for a split-duplicate like this:
A = [1 1.2 3 3.1;
1 1.3 3 3.2;
2 3.9 4 4.1]
and the split-dpulicate column wouldn't get removed
Agood =
1 1.2 3
1 1.3 3
2 3.9 4
I don't know if that's appropriate for your task or not.
