Hongkang Li

Learning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data

M. Wang, Hongkang Li, Shuai Zhang, 2022, 2022 56th Annual Conference on Information Sciences and Systems (CISS).

A Theoretical Understanding of shallow Vision Transformers: Learning, Generalization, and Sample Complexity

M. Wang, Sijia Liu, Pin-Yu Chen, 2023, ICLR.

Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling

M. Wang, Pin-Yu Chen, Jinjun Xiong, 2022, ICML.

On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration

K. Murugesan, Hongkang Li, Shuai Zhang, 2023, 2310.16173.

How Can Context Help? Exploring Joint Retrieval of Passage and Personalized Context

Marina Danilevsky, Songtao Lu, H. Wan, 2023, ArXiv.

A Theoretical Understanding of shallow Vision Transformers: Learning, Generalization, and Sample Complexity

M. Wang, Sijia Liu, Pin-Yu Chen, 2023, ICLR.

Training Nonlinear Transformers for Efficient In-Context Learning: A Theoretical Learning and Generalization Analysis

Hongkang Li, Meng Wang, Pin-Yu Chen, 2024, 2402.15607.

Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis

Hongkang Li, Shuai Zhang, Meng Wang, 2024, 2024 IEEE 13rd Sensor Array and Multichannel Signal Processing Workshop (SAM).

How Does Promoting the Minority Fraction Affect Generalization? A Theoretical Study of One-Hidden-Layer Neural Network on Group Imbalance

Yihua Zhang, Hongkang Li, Shuai Zhang, 2024, IEEE Journal of Selected Topics in Signal Processing.

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding

Hongkang Li, Meng Wang, Pin-Yu Chen, 2024, ICML.