activity
20242026
collaborators

6 papers

cs.LG2026

GradPower: Powering Gradients for Faster Language Model Pre-Training

Jinbo Wang, Mingze Wang, Jiaqi Zhang +5

We propose GradPower, a lightweight gradient-transformation technique for accelerating language model pre-training. Given a gradient vector , GradPower first applies the…

cs.LG2025

The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training

Jinbo Wang, Mingze Wang, Zhanpeng Zhou +3

Transformers consist of diverse building blocks, such as embedding layers, normalization layers, self-attention mechanisms, and point-wise feedforward networks. Thus, understanding…

cs.LG2025

How Transformers Get Rich: Approximation and Dynamics Analysis

Mingze Wang, Ruoxi Yu, Weinan E +1

Transformers have demonstrated exceptional in-context learning capabilities, yet the theoretical understanding of the underlying mechanisms remains limited. A recent work (Elhage e…

cs.LG2024

Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling

Mingze Wang, Zeping Min, Lei Wu

In this work, we investigate the margin-maximization bias exhibited by gradient-based algorithms in classifying linearly separable data. We present an in-depth analysis of the spec…

cs.LG2024

Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent

Liu Ziyin, Mingze Wang, Hongchao Li +1

Symmetries are prevalent in deep learning and can significantly influence the learning dynamics of neural networks. In this paper, we examine how exponential symmetries -- a broad…

cs.LG2024

Improving Generalization and Convergence by Enhancing Implicit Regularization

Mingze Wang, Jinbo Wang, Haotian He +6

In this work, we propose an Implicit Regularization Enhancement (IRE) framework to accelerate the discovery of flat solutions in deep learning, thereby improving generalization and…