activity
20242026
collaborators

7 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…

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.LG2025

Scalable Complexity Control Facilitates Reasoning Ability of LLMs

Liangkai Hang, Junjie Yao, Zhiwei Bai +17

The reasoning ability of large language models (LLMs) has been rapidly advancing in recent years, attracting interest in more fundamental approaches that can reliably enhance their…

cs.LG2024

Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization

Yaoyu Zhang, Leyang Zhang, Zhongwang Zhang +1

Determining whether deep neural network (DNN) models can reliably recover target functions at overparameterization is a critical yet complex issue in the theory of deep learning. T…

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…