search

X-DataInitiative / tick

Module for statistical learning, with a particular emphasis on time-dependent modelling
https://x-datainitiative.github.io/tick/
BSD 3-Clause "New" or "Revised" License
480 stars 105 forks source link

adjacency matrix vs kernel norms matrix #479

Closed DemenzEchtbaer closed 2 years ago

DemenzEchtbaer commented 2 years ago

Thank you for this great tool! Would you kindly explain why the kernel norm matrix and the adjacency matrix end up the same in all cases I encountered, including this "official" example? For exponential kernels (for example), I was under the impression that kernel norms (or branching ratios, isn't it?) were supposed to be alpha/beta...Your insights would be welcome, thanks in advance.

PS: the same happens when using adjust_spectral_radius() in a simulation: this only impacts the adjacency matrix, regardless of the decays.

DemenzEchtbaer commented 2 years ago

Sorry, I'm a bit sleep-deprived: I got mixed up between univariate and multivariate processes! :-P All good now, closing issue.