3 papers
q-bio.NC2026
Balancing structure and randomness: maximum entropy networks for context-dependent computations
Ludwig Hruza, Srdjan Ostojic
Understanding how network function constrains neural connectivity is a central challenge in neuroscience. An influential approach is to train neural networks with gradient descent…
math.PR2025
Structured random matrices and cyclic cumulants: A free probability approach
Denis Bernard, Ludwig Hruza
We introduce a new class of large structured random matrices characterized by four fundamental properties which we discuss. We prove that this class is stable under matrix-valued a…
math.PR2025
Addition to "Structured random matrices and cyclic cumulants: A free probability approach"
Denis Bernard, Ludwig Hruza
We give a refined definition of the class of random matrix ensembles introduced in our paper "Structured random matrices and cyclic cumulants: A free probability approach" (arXiv:2…