Profiles2024-2026
Chenyang Zhang
The University of Hong Kong
6Papers
0Last author
9Unique co-authors
4First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers6
- Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNsAuthor 3 of 4AAAI 2026 · 3 citations
- Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient DescentAuthor 1 of 2ICML 2026 · 1 citation
- Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher ModelsAuthor 1 of 4ICLR 2026
- On the Robustness of Transformers against Context Hijacking for Linear ClassificationAuthor 2 of 6NeurIPS 2025 · 7 citations
- Transformer Learns Optimal Variable Selection in Group-Sparse ClassificationAuthor 1 of 3ICLR 2025
- The Implicit Bias of Adam on Separable DataAuthor 1 of 3NeurIPS 2024 · 37 citations
