Zihan Wang

PhD student, New York University

Joined

May 2023

Names

Zihan Wang (Preferred)

Emails

****@nyu.edu (Confirmed)

Personal Links

Career & Education History

PhD student

New York University (nyu.edu)

2024 – Present

MS student

New York University (nyu.edu)

2022 – 2024

Undergrad student

Peking University (pku.edu.cn)

2018 – 2022

Advisors, Relations & Conflicts

No relations added

Expertise

Domain adaptation

2024 – Present

Deep learning theory

2022 – Present

Federated learning

2022 – 2023

Publications

When does Chain-of-Thought Help: A Markovian Perspective
Zihan Wang, Yijun Dong, Qi Lei
- LIT Workshop @ ICLR 2026
- Readers: Everyone
Understanding Adam through the Lens of Duality: A Unified Theory of Normalized Gradient Methods
Danny Hyun Ho Son, Matus Telgarsky, Zihan Wang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Data Reconstruction Attacks and Defenses: A Systematic Evaluation
Sheng Liu, Zihan Wang, Yuxiao Chen, Qi Lei
- AISTATS 2025 Poster
- Readers: Everyone
Elastic Representation: Mitigating Spurious Correlations for Group Robustness
Tao Wen, Zihan Wang, Quan Zhang, Qi Lei
- AISTATS 2025 Poster
- Readers: Everyone
Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
Arthur Jacot, Peter Súkeník, Zihan Wang, Marco Mondelli
- ICLR 2025 Oral
- Readers: Everyone
Implicit bias of SGD in L2-regularized linear DNNs: One-way jumps from high to low rank
Zihan Wang, Arthur Jacot
- ICLR 2024
- Readers: Everyone
A Theoretical and Empirical Analysis on Reconstruction Attacks and Defenses
Sheng Liu, Zihan Wang, Qi Lei
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank
Zihan Wang, Arthur Jacot
- ICLR 2024 spotlight
- Readers: Everyone
Reconstructing Training Data from Model Gradient, Provably
Zihan Wang, Jason D. Lee, Qi Lei
- Published: 01 Jan 2022, Last Modified: 17 May 2023
- CoRR 2022
- Readers: Everyone

Co-Authors