11 papers
Diffusion Models for Sampling Near Criticality in Lattice Field Theories
Yang-yang Tan, Gert Aarts, Diaa E. Habibi +2
We investigate generative diffusion models as denoising samplers for two- and three-dimensional lattice theory across the symmetric, near-critical, and broken phases. Valida…
Spectral phase transitions and trainability in neural network learning dynamics
Chanju Park, Dario Bocchi, Francesco D'Amico +2
The emergence of low-dimensional structures in the spectra of neural network weight matrices is a common empirical feature of trained models, but the dynamical origin of this pheno…
Finite-temperature Yang-Mills theories with the density of states method: towards the continuum limit
Ed Bennett, Biagio Lucini, David Mason +4
A first-order, confinement/deconfinement phase transition appears in the finite temperature behavior of many non-Abelian gauge theories. These theories play an important role in pr…
Phase diagram and eigenvalue dynamics of stochastic gradient descent in multilayer neural networks
Chanju Park, Biagio Lucini, Gert Aarts
Hyperparameter tuning is one of the essential steps to guarantee the convergence of machine learning models. We argue that intuition about the optimal choice of hyperparameters for…
Chimera baryons and mesons on the lattice: a spectral density analysis
Ed Bennett, Luigi Del Debbio, Niccolò Forzano +10
We develop and test a spectral-density analysis method, based on the introduction of smeared energy kernels, to extract physical information from two-point correlation functions co…
Exploring Generative Networks for Manifolds with Non-Trivial Topology
Shiyang Chen, Gert Aarts, Biagio Lucini
The expressive power of neural networks in modelling non-trivial distributions can in principle be exploited to bypass topological freezing and critical slowing down in simulations…