Xiang Wang

PhD student, Duke University

Joined

August 2018

Names

Xiang Wang (Preferred)

Emails

****@cs.duke.edu (Confirmed)

****@duke.edu (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

PhD student

Duke University (duke.edu)

2017 – Present

Undergrad student

Shanghai Jiao Tong University (sjtu.edu.cn)

2013 – 2017

Advisors, Relations & Conflicts

PhD Advisor

Rong Ge

2017 – Present

Expertise

non-convex optimization

2017 – Present

deep learning theory

2017 – Present

Publications

Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
Muthu Chidambaram, Xiang Wang, Chenwei Wu, Rong Ge
- ICML 2023 Poster
- Readers: Everyone
Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
Muthu Chidambaram, Xiang Wang, Chenwei Wu, Rong Ge
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- Submitted to ICLR 2023
- Readers: Everyone
Understanding Edge-of-Stability Training Dynamics with a Minimalist Example
Xingyu Zhu, Zixuan Wang, Xiang Wang, Mo Zhou, Rong Ge
- Published: 01 Feb 2023, Last Modified: 17 Feb 2023
- ICLR 2023 poster
- Readers: Everyone
Plateau in Monotonic Linear Interpolation --- A "Biased" View of Loss Landscape for Deep Networks
Xiang Wang, Annie N. Wang, Mo Zhou, Rong Ge
- Published: 01 Feb 2023, Last Modified: 14 Feb 2023
- ICLR 2023 poster
- Readers: Everyone
Towards Understanding the Data Dependency of Mixup-style Training
Muthu Chidambaram, Xiang Wang, Yuzheng Hu, Chenwei Wu, Rong Ge
- Published: 28 Jan 2022, Last Modified: 12 Oct 2025
- ICLR 2022 Spotlight
- Readers: Everyone
Towards Demystifying Representation Learning with Non-contrastive Self-supervision
Xiang Wang, Xinlei Chen, Simon Shaolei Du, Yuandong Tian
- Published: 28 Jan 2022, Last Modified: 12 Oct 2025
- ICLR 2022 Submitted
- Readers: Everyone
Understanding Deflation Process in Over-parametrized Tensor Decomposition
Rong Ge, Yunwei Ren, Xiang Wang, Mo Zhou
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Poster
- Readers: Everyone
Beyond Lazy Training for Over-parameterized Tensor Decomposition
Xiang Wang, Chenwei Wu, Jason D. Lee, Tengyu Ma, Rong Ge
- 06 May 2021
- OpenReview Archive Direct Upload
- Readers: Everyone
Guarantees for Tuning the Step Size using a Learning-to-Learn Approach
Xiang Wang, Shuai Yuan, Chenwei Wu, Rong Ge
- 28 Sept 2020 (modified: 12 Oct 2025)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone

Xiang Wang

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Co-Authors