activity
20182026
most citedFermionic Machine Learning

1 citations · 1 across the 6 of their papers we have counts for

collaborators

8 papers

cs.LG2026

Hidden Activations are not Enough I: Knowledge Matrices as Higher Representations

Marco Armenta

We study the knowledge matrix of a trained feedforward network as a higher representation of its inputs. A network is a pair , a thin representation of its quiver and an…

math.KT2026

The Serre--Hochschild plane of a finite-dimensional algebra

Marco Armenta

For a finite-dimensional algebra over a field we organize the Hochschild cohomology of with coefficients in all derived tensor powers of the Serre bimodule $ω=\D A$ into a…

math.RT2026

Protected corners and a trichotomy for Han's conjecture

Marco Armenta

Han's conjecture predicts that a finite-dimensional algebra with eventually vanishing Hochschild homology has finite global dimension. In the tau-Hochschild framework of Cibils, La…

math.RT2026

-Hochschild (co)homology, the square of the Serre bimodule, and the Coxeter automorphism of the Tamarkin--Tsygan calculus

Marco Armenta

We relate two recent enrichments of the Hochschild theory of a finite-dimensional algebra $\Lm$: the -Hochschild (co)homology of Cibils, Lanzilotta, Marcos and Solotar, built fr…

math.RT2026

The Coxeter transformation as an automorphism of the Tamarkin--Tsygan calculus

Marco Armenta

Let be a finite-dimensional algebra over a field $\kk$. We show that the Auslander--Reiten bimodule $\ar_A:=\D A[-1]$ is central in the derived Picard group of and that, wh…

cs.LG2024

Hidden Activations Are Not Enough: A General Approach to Neural Network Predictions

Samuel Leblanc, Aiky Rasolomanana, Marco Armenta

We introduce a novel mathematical framework for analyzing neural networks using tools from quiver representation theory. This framework enables us to quantify the similarity betwee…

quant-ph2024★ 1 cited

Fermionic Machine Learning

Jérémie Gince, Jean-Michel Pagé, Marco Armenta +2

We introduce fermionic machine learning (FermiML), a machine learning framework based on fermionic quantum computation. FermiML models are expressed in terms of parameterized match…

math.KT2018

Batalin-Vilkovisky structure on Hochschild cohomology with coefficients in the dual algebra

Marco Armenta, Samuel Leblanc

We prove that Hochschild cohomology with coefficients in $A^*=\Hom_k(A,k)$ under conditions on the algebra structure of is a Batalin-Vilkovisky algebra. We also show that for…