# On the exact learnability of graph parameters: The case of partition functions

13 Jun 2016Nadia LabaiJohann A. Makowsky

We study the exact learnability of real valued graph parameters $f$ which are known to be representable as partition functions which count the number of weighted homomorphisms into a graph $H$ with vertex weights $\alpha$ and edge weights $\beta$. M. Freedman, L. Lov\'asz and A. Schrijver have given a characterization of these graph parameters in terms of the $k$-connection matrices $C(f,k)$ of $f$... (read more)

PDF Abstract

No code implementations yet. Submit your code now