4 papers
Fast Generalization after Interpolation via Critically Damped Momentum Optimization
Luca Muscarnera, Silas Ruhrberg Estévez, Yuanzhang Xiao +1
A central problem in machine learning is that models can achieve near-perfect training performance while generalizing substantially less well to unseen examples. This gap is especi…
Knowledge-Informed Kernel State Reconstruction from Heterogeneous Partial Observations
Luca Muscarnera, Silas Ruhrberg Estévez, Samuel Holt +2
Real-world scientific systems are rarely observed through complete, regularly sampled state trajectories. Instead, measurements are often partial, noisy, and heterogeneous, providi…
Elimination-compensation pruning for fully-connected neural networks
Enrico Ballini, Luca Muscarnera, Alessio Fumagalli +2
The unmatched ability of Deep Neural Networks in capturing complex patterns in large and noisy datasets is often associated with their large hypothesis space, and consequently to t…
Emergence of Structure in Ensembles of Random Neural Networks
Luca Muscarnera, Luigi Loreti, Giovanni Todeschini +2
Randomness is ubiquitous in many applications across data science and machine learning. Remarkably, systems composed of random components often display emergent global behaviors th…