9 papers
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…
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.…
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…
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…
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…
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…