8 citations · 9 across the 4 of their papers we have counts for
6 papers
Complete collineations for maximum likelihood estimation
Gergely Bérczi, Eloise Hamilton, Philipp Reichenbach +1
We import the algebro-geometric notion of a complete collineation into the study of maximum likelihood estimation in directed Gaussian graphical models. A complete collineation pro…
Symmetries in Directed Gaussian Graphical Models
Visu Makam, Philipp Reichenbach, Anna Seigal
We define Gaussian graphical models on directed acyclic graphs with coloured vertices and edges, calling them RDAG (restricted directed acyclic graph) models. If two vertices or ed…
Barriers for recent methods in geodesic optimization
Cole Franks, Philipp Reichenbach
We study a class of optimization problems including matrix scaling, matrix balancing, multidimensional array scaling, operator scaling, and tensor scaling that arise frequently in…
Toric invariant theory for maximum likelihood estimation in log-linear models
Carlos Améndola, Kathlén Kohn, Philipp Reichenbach +1
We establish connections between invariant theory and maximum likelihood estimation for discrete statistical models. We show that norm minimization over a torus orbit is equivalent…
Tensor Rank and Complexity
Giorgio Ottaviani, Philipp Reichenbach
These lecture notes are intended as an introduction to several notions of tensor rank and their connections to the asymptotic complexity of matrix multiplication. The latter is stu…
Invariant theory and scaling algorithms for maximum likelihood estimation
Carlos Améndola, Kathlén Kohn, Philipp Reichenbach +1
We uncover connections between maximum likelihood estimation in statistics and norm minimization over a group orbit in invariant theory. We focus on Gaussian transformation familie…