collaborators

6 papers

cs.LG2026

Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient Descent

Chenyang Zhang, Yuan Cao

Transformers have demonstrated remarkable in-context learning (ICL) capabilities. The strong ICL performance of transformers is commonly believed to arise from their ability to imp…

cs.LG2026

Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models

Chenyang Zhang, Qingyue Zhao, Quanquan Gu +1

Transformers have achieved great success across a wide range of applications, yet the theoretical foundations underlying their success remain largely unexplored. To demystify the s…

cs.LG2025

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

Xuan Tang, Han Zhang, Yuan Cao +1

Adam is a popular and widely used adaptive gradient method in deep learning, which has also received tremendous focus in theoretical research. However, most existing theoretical wo…

stat.ML2025

Transformer Learns Optimal Variable Selection in Group-Sparse Classification

Chenyang Zhang, Xuran Meng, Yuan Cao

Transformers have demonstrated remarkable success across various applications. However, the success of transformers have not been understood in theory. In this work, we give a case…

stat.ML2025

Gradient Descent Robustly Learns the Intrinsic Dimension of Data in Training Convolutional Neural Networks

Chenyang Zhang, Peifeng Gao, Difan Zou +1

Modern neural networks are usually highly over-parameterized. Behind the wide usage of over-parameterized networks is the belief that, if the data are simple, then the trained netw…

cs.CL2025

On the Robustness of Transformers against Context Hijacking for Linear Classification

Tianle Li, Chenyang Zhang, Xingwu Chen +2

Transformer-based Large Language Models (LLMs) have demonstrated powerful in-context learning capabilities. However, their predictions can be disrupted by factually correct context…