Postdoctoral Associate
Massachusetts Institute of TechnologyI develop machine learning methods and scalable algorithms for mathematical optimization.
H-PDLP: GPU-Accelerated Linear Programming via Generalized PDHG and Homogeneous Self-Dual Embedding
Preprint, 2026
Develops a generalized primal-dual hybrid gradient method for a compact homogeneous self-dual embedding with linear convergence guarantees. Enables matrix-free GPU computation of solutions and infeasibility certificates for large-scale linear programs.
Learning to Optimize for Mixed-Integer Non-linear Programming with Feasibility Guarantees
INFORMS Journal on Computing (Major revision)
Learns to solve parametric mixed-integer nonlinear programs without an optimization solver at training and inference time, using differentiable integer correction and feasibility projection with theoretical guarantees. Produces feasible, high-quality solutions within milliseconds.
PyEPO: A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming
Mathematical Programming Computation, 2024
Introduces a unified framework and benchmarks integrating linear and integer programming solvers with PyTorch and JAX for decision-focused learning, which trains predictive models on the quality of the decisions they lead to rather than on prediction error alone.
I am a postdoctoral associate at MIT Sloan, working with Haihao Lu.
I develop machine learning methods and scalable algorithms for mathematical optimization, with a focus on GPU-accelerated optimization, learning to optimize, and decision-focused learning.