3 papers
cond-mat.dis-nn2025
Spring-block theory of feature learning in deep neural networks
Cheng Shi, Liming Pan, Ivan DokmaniÄ
Feature-learning deep nets progressively collapse data to a regular low-dimensional geometry. How this emerges from the collective action of nonlinearity, noise, learning rate, and…
cs.LG2025
Joint Graph Rewiring and Feature Denoising via Spectral Resonance
Jonas Linkerhägner, Cheng Shi, Ivan DokmaniÄ
When learning from graph data, the graph and the node features both give noisy information about the node labels. In this paper we propose an algorithm to jointly denoise the featu…
physics.geo-ph2024
High-Rate Phase Association with Travel Time Neural Fields
Cheng Shi, Giulio Poggiali, Chris Marone +2
Earthquake science and seismology rely on the ability to associate seismic waves with their originating earthquakes. Earthquake detection algorithms based on deep learning have pro…