activity
20242026
collaborators

7 papers

cond-mat.dis-nn2026

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…

hep-lat2026

Stochastic Path Sampler For Lattice Field Theory

Shiyang Chen, Moxian Qian, Gert Aarts +2

In lattice field theory, target distributions are known only up to normalization, (\tildeπ(ϕ)\propto e^{-S(ϕ)}), while the partition function is intractable. Markov chain Monte…

cond-mat.dis-nn2025

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…

hep-lat2025

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…

hep-lat2024

Random Matrix Theory for Stochastic Gradient Descent

Chanju Park, Matteo Favoni, Biagio Lucini +1

Investigating the dynamics of learning in machine learning algorithms is of paramount importance for understanding how and why an approach may be successful. The tools of physics a…

cond-mat.dis-nn2024

Stochastic weight matrix dynamics during learning and Dyson Brownian motion

Gert Aarts, Biagio Lucini, Chanju Park

We demonstrate that the update of weight matrices in learning algorithms can be described in the framework of Dyson Brownian motion, thereby inheriting many features of random matr…