3 papers
cond-mat.dis-nn2026
Dataset Complexity Shapes Finite-Distance Loss Geometry in Neural Networks
Jaeyong Bae, Hawoong Jeong
Finite datasets can share the same size and low-order statistics while differing strongly in structural complexity. We connect this dataset complexity to loss-landscape geometry by…
cond-mat.stat-mech2026
Opinion Formation in a Spatially Constrained Coevolving Nonlinear Voter Model
Phil Gwon Kim, Jaeyong Bae, Jaeseok Hur +1
We investigate a spatially constrained coevolving nonlinear voter model. Using a random geometric graph, we constrain the interaction range of voter dynamics. If local rewiring is…
cs.LG2024
Exploring how deep learning decodes anomalous diffusion via Grad-CAM
Jaeyong Bae, Yongjoo Baek, Hawoong Jeong
While deep learning has been successfully applied to the data-driven classification of anomalous diffusion mechanisms, how the algorithm achieves the feat still remains a mystery.…