graphpku / jacobiconv Goto Github PK

Dear authors,

Thanks for sharing the code of the excellent work.

I notice that the implementation of Jacobi basis is different from the gold form of recurrence relations of Jacobi polynomials, as it introduces extra two parameters l and r. Although the two versions are equivalent when fixing l=-1 and r=1, I wonder what the source of the recurrence formula corresponding to the implementation.

Besides, I aslo notice that in line 148 of the file impl/PolyConv.py, the variable tmp2_2 has a negative before it. If simply considering the a parameter as beta of Jacobi polynomials and the b parameter as alpha, the coef1 (line 134) should have a negative also. I wonder if this is my misunderstanding on the implementation.

Very thanks for your attention and reply!

First of all, thank you for your great work. After reading your paper, I have a question: How are the proportions of multiple eigenvalues in Table 7 in the appendix calculated? I used the same data set to calculate the proportion of multiple eigenvalues, and the results far exceeded those in Table 7. If it's convenient, can you provide the relevant code?

Dear authors,

Thanks for sharing the code of the excellent work JacobiConv.
Recently, I try to re-implement the model and met a question on the implementation of JacobiConv.

The recurrence relations of Jacobi polynomials have the form
$$P_n(L) = A_n * L * P_{n-1}(L) + B_n * P_{n-1}(L) + C_n * P_{n-2}(L)$$
where $B_n = \frac{a^2-b^2}{2n(n+a+b)(2n+a+b-2)}$.
However, I notice that in line 148 of the file impl/PolyConv.py, the variable tmp2_2, which in my opinion represents $B_n$, has a negative before it.
I wonder if this is my misunderstanding on the implementation, or just a mistake in the code?

Very thanks for your attention and reply!