About

My research lies at the intersection of machine learning and mathematical optimization. I focus on large-scale optimization on modern computing hardware, learning to optimize, and learning for decision-making.

I investigate how optimization algorithms can make effective use of modern hardware, particularly GPUs, to solve larger problems more efficiently. My work on learning to optimize explores how learning can guide and accelerate the solution of complex optimization problems. In decision-focused learning, I study how predictive models can be trained for the quality of the decisions they inform.

I aim to bring together algorithms, AI, and modern hardware to make optimization more useful in practice. Faster and more scalable methods can support planning with more realistic models and enable timely decisions as conditions change. By building these advances into open-source computational infrastructure, I hope to broaden where optimization can be used and improve the decisions it supports.

I am a postdoctoral associate at the MIT Sloan School of Management, working with Haihao Lu.

I received my PhD in Operations Research from the University of Toronto in 2025, advised by Elias B. Khalil.

In 2023, I was a research intern at Pacific Northwest National Laboratory, where I studied learning-based correction methods for mixed-integer nonlinear optimization.