7 papers
Looped Transformers with Layer Normalization Provably Learn the Power Method
Lyumin Wu, Chenyang Zhang, Yuan Cao
Transformers have achieved remarkable success across a wide range of applications, and a growing body of work suggests that part of their strength comes from their ability to learn…
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…
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…
Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs
Zhongjie Shi, Puyu Wang, Chenyang Zhang +1
Modern deep learning techniques focus on extracting intricate information from data to achieve accurate predictions. However, the training datasets may be crowdsourced and include…
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…
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…