About Me

Hello! I’m an MSc student in Computer Science at the University of British Columbia supervised by Mark Schmidt.

I am interested in optimization for deep learning, deep learning theory and generative models. My goal is to understand neural network training dynamics and why adaptive optimizers are so effective for modern deep learning problems e.g. LLMs. On the application side, I am interested in generative models e.g. diffusion and flow matching to enhance discovery in scientific fields.

During my undergraduate studies, I was fortunate to work with Zhiyuan Li and Tianhao Wang at TTIC; Peter Richtárik at KAUST; and Mark Schmidt, Renjie Liao, and Leonid Sigal at UBC.

News

[10/2025] Our workshop paper was accepted for an oral presentation! I will be giving a short talk on sign descent and heavy-tailed class imbalance at the NeurIPS OPT workshop.

[09/2025] Two papers accepted to NeurIPS 2025!

[09/2024] Spotlight paper on the Adam optimizer and heavy-tailed class imbalance at NeurIPS 2024!