I am a PhD candidate in Computer Science at Cornell University, supervised by Chris De Sa. Currently, I am interning at Inria in Paris, working with Adrien Taylor, Baptiste Goujaud, and Aymeric Dieuleveut.

In 2024, I was an intern at the ELLIS Institute Tübingen / Max Planck Institute for Intelligent Systems, hosted by Antonio Orvieto. I also spent two summers in NYC at the Flatiron Institute, Center for Computational Mathematics, where I worked with Robert Gower. In 2020, I received my MSc degree in Computer Science from the University of British Columbia, advised by Mark Schmidt.

I am interested in understanding and developing optimization algorithms for large-scale machine learning.

Preprints

• Gradient Descent on Logistic Regression with Non-Separable Data and Large Step Sizes
  Si Yi Meng, Antonio Orvieto, Daniel Cao, Chris De Sa
  2024 (In submission)
  

Publications

• A Model-Based Method for Minimizing CVaR and Beyond
  Si Yi Meng, Robert M. Gower
  ICML 2023
  

• A General Analysis of Example-Selection for Stochastic Gradient Descent
  Yucheng Lu*, Si Yi Meng*, Chris De Sa
  ICLR 2022 (Spotlight)
  

• Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation
  Si Yi Meng*, Sharan Vaswani*, Issam H. Laradji, Mark Schmidt, Simon Lacoste-Julien
  AISTATS 2020
  

• UD Co-Spaces: A Table-Centred Multi-Display Environment for Public Engagement in Urban Design Charrettes
  Narges Mahyar, Kelly J. Burke, Jialiang Xiang, Si Yi Meng, Kellogg S. Booth, Cynthia L. Girling, Ronald W. Kellett
  ACM ISS 2016 (Honorable mention)
  

  ^{* indicates equal contribution}