activity
20242026
most citedArchitecture Induces Structural Invariant Manifolds of Neural Network Training Dynamics

1 citations · 1 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2026

Gradient Flow Dynamics and Implicit Bias of Diagonal Linear Networks under Infinitesimal Initialization

Jiajie Zhao, Jianxing Wang, Junjie Yang +2

We study the gradient flow dynamics of diagonal linear networks for regression tasks under infinitesimal initialization. Extending Theorem 1 from Pesme & Flammarion (2023), we gene…

cs.LG2026

Towards Understanding Adam Convergence on Highly Degenerate Polynomials

Zhiwei Bai, Jiajie Zhao, Zhangchen Zhou +2

Adam is a widely used optimization algorithm in deep learning, yet the specific class of objective functions where it exhibits inherent advantages remains underexplored. Unlike pri…

math.DS2025★ 1 cited

Architecture Induces Structural Invariant Manifolds of Neural Network Training Dynamics

Jiajie Zhao, Tao Luo, Yaoyu Zhang

While architecture is recognized as key to the performance of deep neural networks, its precise effect on training dynamics has been unclear due to the confounding influence of dat…

cs.LG2025

Adaptive Preconditioners Trigger Loss Spikes in Adam

Zhiwei Bai, Zhangchen Zhou, Jiajie Zhao +6

Loss spikes commonly emerge during neural network training with the Adam optimizer across diverse architectures and scales, yet their underlying mechanism remains elusive. While pr…

cs.LG2024

Disentangle Sample Size and Initialization Effect on Perfect Generalization for Single-Neuron Target

Jiajie Zhao, Zhiwei Bai, Yaoyu Zhang

Overparameterized models like deep neural networks have the intriguing ability to recover target functions with fewer sampled data points than parameters (see arXiv:2307.08921). To…

cs.LG2024

Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion

Zhiwei Bai, Jiajie Zhao, Yaoyu Zhang

Matrix factorization models have been extensively studied as a valuable test-bed for understanding the implicit biases of overparameterized models. Although both low nuclear norm a…