3 papers
cs.LG2026
Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks
Andrew Cheng, Ali Eslamian, Jie Cheng +2
Neural networks can often be trained or fine-tuned through random low-dimensional reparameterization, where a small latent vector is mapped into a full parameter update by a frozen…
cs.LG2025
GraphMinNet: Learning Dependencies in Graphs with Light Complexity Minimal Architecture
Md Atik Ahamed, Andrew Cheng, Qiang Ye +1
Graph Neural Networks (GNNs) have demonstrated remarkable success in various applications, yet they often struggle to capture long-range dependencies (LRD) effectively. This paper…
math.OC2024
Structured Regularization for Constrained Optimization on the SPD Manifold
Andrew Cheng, Melanie Weber
Matrix-valued optimization tasks, including those involving symmetric positive definite (SPD) matrices, arise in a wide range of applications in machine learning, data science and…