About Me
I am a second-year Ph.D. student in the ECE department at Princeton University, advised by Prof. Jason D. Lee. My research interests lie broadly in Machine Learning Theory and Applied Probability.
I received B.S. in Computer Science from Shanghai Jiao Tong University and was a member of the SJTU ACM Honors Class. After that, I received M.S. in Machine Learning from Carnegie Mellon University. I was fortunate to work with Prof. Rong Ge and Prof. Yuanzhi Li during those days.
Email: yunwei DOT ren AT princeton DOT edu
Publications
(a-b) indicates alphabetical ordering; * means equal contribution.
-
Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis.
Yunwei Ren, Jason D. Lee.
In submission. -
Learning and Transferring Sparse Contextual Bigrams with Linear Transformers.
*Yunwei Ren, *Zixuan Wang, Jason D. Lee.
Conference on Neural Information Processing Systems (NeurIPS), 2024. -
On the Importance of Contrastive Loss in Multimodal Learning.
Yunwei Ren, Yuanzhi Li.
Preprint, 2023. -
Depth-Separation with Multilayer Mean-Field Networks. [Slides]
Yunwei Ren, Mo Zhou, Rong Ge.
International Conference on Learning Representations (ICLR), 2023. (Spotlight) -
Understanding Deflation Process in Over-parametrized Tensor Decomposition.
(a-b) Rong Ge, Yunwei Ren, Xiang Wang, Mo Zhou.
Conference on Neural Information Processing Systems (NeurIPS), 2021.