activity
20242026
collaborators

9 papers

cs.LG2026

Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization

Marcelina Marjankowska, Valerio Modugno, Paolo Barucca

Hessian spectral properties are a standard tool in analysing neural-network training, with eigenvalues linked to sharpness, generalization, and optimization dynamics. Eigenvalues q…

cs.SI2026

Maximum entropy temporal networks

Paolo Barucca

Temporal networks consist of timestamped directed interactions that may appear continuously in time, yet few studies have directly tackled the continuous-time modeling of networks.…

cond-mat.dis-nn2026

Fundamental Limits of Stability Inference in High-Dimensional Complex Systems

Michela Costa, Kentaro Hoshisashi, Flaviano Morone +2

Many complex systems, including ecosystems, neural circuits, and financial markets, are inferred to operate close to a threshold of instability, at which a small perturbation can p…

cs.LG2026

Physics-Informed Neural Networks for Solving Derivative-Constrained PDEs

Kentaro Hoshisashi, Carolyn E Phelan, Paolo Barucca

Physics-Informed Neural Networks (PINNs) recast PDE solving as an optimisation problem in function space by minimising a residual-based objective, yet many applications require add…

cs.SI2025

Parsimonious Hawkes Processes for temporal networks modelling

Yuwei Zhu, Paolo Barucca

Temporal networks are characterised by interdependent link events between nodes, forming ordered sequences of links that may represent specific information flows in the system. Nev…

q-fin.MF2025

How low-cost AI universal approximators reshape market efficiency

Paolo Barucca, Flaviano Morone

The efficient market hypothesis (EMH) famously stated that prices fully reflect the information available to traders. This critically depends on the transfer of information into pr…