I would like to use GLM to approximate an integer variable as following a Poisson distribution where the rate parameter is determined by a the independent variable X. X lives in a non-Euclidean space, and so using vanilla GLM tends to not provide a very good fit. I was thinking of making use of laplacian regularisation to improve the fit. My understanding is that I can add a regularisation term given by \alpha X'\beta L \beta' X where \beta is a vector of regression coefficients, L is the laplacian of my non-euclidean manifold and \alpha is regularisation cost. Is there a package that can do this? My understanding is that GLM.jl does not support regularisation. I also looked at MLJLinearModels.jl, but I couldn’t figure out how to add custom regularisation.