3 papers
cond-mat.stat-mech2026
The bliss of dimensionality: how an unsupervised criterion identifies optimal low-resolution representations of high-dimensional datasets
Margherita Mele, Daniel Campos Moreno, Raffaello Potestio
Selecting the optimal resolution for discretizing high-dimensional data is a central problem in physics and data analysis, particularly in unsupervised settings where the underlyin…
cond-mat.stat-mech2024
Density of states in neural networks: an in-depth exploration of learning in parameter space
Margherita Mele, Roberto Menichetti, Alessandro Ingrosso +1
Learning in neural networks critically hinges on the intricate geometry of the loss landscape associated with a given task. Traditionally, most research has focused on finding spec…
cond-mat.soft2022
Information-theoretical measures identify accurate low-resolution representations of protein configurational space
Margherita Mele, Roberto Covino, Raffaello Potestio
A steadily growing computational power is employed to perform molecular dynamics simulations of biological macromolecules, which represents at the same time an immense opportunity…