activity
20232026
most citedGeometry of Polynomial Neural Networks

3 citations · 3 across the 10 of their papers we have counts for

collaborators

13 papers

math-ph2026

An edge-bicolored graph approach to the Ising model on random regular graphs

Michael Borinsky, Shiyue Ren, Maximilian Wiesmann

We give an exact solution of the ferromagnetic Ising model on a random regular graph ensemble via analytic combinatorics. Expressing the partition function as the generating functi…

math.CO2026

Asymptotic number of edge-colored regular graphs

Michael Borinsky, Chiara Meroni, Maximilian Wiesmann

We prove a formula for the asymptotic number of edge-colored regular graphs with a prescribed set of allowed vertex-incidence structures. The formula depends on specific critical p…

math.CO2026

Lee-Yang phenomena in edge-coloured graph counting

Maximilian Wiesmann

We study the accumulation of zeros of a polynomial arising from the enumeration of edge-coloured graphs along certain limit curves. The polynomial is a variant of an edge-chromatic…

math.AG2025

The Maximum Likelihood Degree of Toric Models is Monotonic

Carlos Améndola, Janike Oldekop, Maximilian Wiesmann

We settle a conjecture by Coons and Sullivant stating that the maximum likelihood (ML) degree of a facial submodel of a toric model is at most the ML degree of the model itself. We…

math.AC2025

Squared Linear Models

Hannah Friedman, Bernd Sturmfels, Maximilian Wiesmann

We study statistical models that are parametrized by squares of linear forms. All critical points of the likelihood function are real and positive. There is one critical point in e…

math.AC2025

The Likelihood Correspondence

Thomas Kahle, Hal Schenck, Bernd Sturmfels +1

An arrangement of hypersurfaces in projective space is strict normal crossing (SNC) if and only if its Euler discriminant is nonzero. We study the critical loci of arbitrary Lauren…

math.AC2024

Arrangements and Likelihood

Thomas Kahle, Lukas Kühne, Leonie Mühlherr +2

We develop novel tools for computing the likelihood correspondence of an arrangement of hypersurfaces in a projective space. This uses the module of logarithmic derivations. This o…

math.CO2024

Bivariate exponential integrals and edge-bicolored graphs

Michael Borinsky, Chiara Meroni, Maximilian Wiesmann

We show that specific exponential bivariate integrals serve as generating functions of labeled edge-bicolored graphs. Based on this, we prove an asymptotic formula for the number o…

math.AG2024

Euler Stratifications of Hypersurface Families

Simon Telen, Maximilian Wiesmann

We stratify families of projective and very affine hypersurfaces according to their topological Euler characteristic. Our new algorithms compute all strata using algebro-geometric…

stat.ML2024

Pathological Regularization Regimes in Classification Tasks

Maximilian Wiesmann, Paul Larsen

In this paper we demonstrate the possibility of a trend reversal in binary classification tasks between the dataset and a classification score obtained from a trained model. This t…

math.AG2024★ 3 cited

Geometry of Polynomial Neural Networks

Kaie Kubjas, Jiayi Li, Maximilian Wiesmann

We study the expressivity and learning process for polynomial neural networks (PNNs) with monomial activation functions. The weights of the network parametrize the neuromanifold. I…

math.AG2023

Algebraic Geometry of Quantum Graphical Models

Eliana Duarte, Dmitrii Pavlov, Maximilian Wiesmann

Algebro-geometric methods have proven to be very successful in the study of graphical models in statistics. In this paper we introduce the foundations to carry out a similar study…

math.AG2023

Toric Fiber Products in Geometric Modeling

Eliana Duarte, Benjamin Hollering, Maximilian Wiesmann

An important challenge in Geometric Modeling is to classify polytopes with rational linear precision. Equivalently, in Algebraic Statistics one is interested in classifying scaled…