About me

I am a Ph.D. student in Operations Research at the H. Milton Stewart School of Industrial and Systems Engineering (ISyE), Georgia Institute of Technology. Before joining Georgia Tech, I received my B.S. in Applied Mathematics (Honors, Concentration in Statistics) and B.A. in Computer Science from Bucknell University, graduating Summa Cum Laude.

My research sits at the intersection of optimization and machine learning, with a focus on:

• Combinatorial optimization and integer programming — exact methods, decomposition, heuristics, and metaheuristics for hard discrete problems
• Machine learning for operations research — optimization proxies for decomposition methods, and learning-based contextual stochastic optimization for real-time, large-scale decision making
• Online learning and bandits — Pareto-regret bounds for stochastic and adversarial multi-objective bandits
• Covering arrays and combinatorial interaction testing — structure of optimal solutions under constraints
• Matrix analysis — numerical ranges and Crouzeix’s conjecture

My recent work includes the Proxy Benders Decomposition, which replaces Benders subproblem optimization with certified optimization proxies; end-to-end supply chain planning in the paper industry via column generation and Benders decomposition; Pareto-regret bounds for stochastic and adversarial multi-objective bandits; learning optimization proxies for real-time order fulfillment; and OPTAgent, which uses LLM agents to synthesize solver-selection policies (NeurIPS 2026 ML×OR Workshop). See my publications and research projects for details.

News

• Oct 2026 — Our paper OPTAgent: From Standalone Solvers to Deployment-Aware Solver Ecosystems (co-first author, with Hanyang Jiang, Miao Li, Danlin Li, Sikai Cheng, Pascal Van Hentenryck, and Russell Bent) was accepted to the NeurIPS 2026 Workshop on ML×OR!
• Oct 2026 — Our paper Match the Canvas, Not Just the Answer: Predictability-Aware SFT for Diffusion Language Models (with Miao Li, Hanyang Jiang, Pascal Van Hentenryck, and others) is on arXiv!
• Sep 2026 — Our paper The Role of Coordinates in Pareto Regret for Adversarial Multi-Objective Bandits (with Mengfan Xu) is on arXiv!
• Jul 2026 — Our paper End-to-End Supply Chain Planning in the Paper Industry Via Column Generation and Benders Decomposition (with Amira Hijazi and Pascal Van Hentenryck) is on arXiv!
• Jul 2026 — Our paper Optimal Combinatorial Testing with Constraints: The Balancing Act (with Thiago Serra, Hunter Gehman, Sumit Dhar, Mikey Ferguson, John Hooker, and Marcel Schoppers) is on arXiv!
• Jun 2026 — The extended version of our order fulfillment work, Learning Optimization Proxies for Sequential Contextual Stochastic Programs (with Tinghan Ye, Shuaicheng Tong, Beste Basciftci, and Pascal Van Hentenryck), is on arXiv!
• Jun 2026 — Our paper The Proxy Benders Decomposition (with El Mehdi Er Raqabi, Mathieu Tanneau, and Pascal Van Hentenryck) is on arXiv!
• Apr 2026 — Our paper Are Stochastic Multi-objective Bandits Harder than Single-objective Bandits? (with Mengfan Xu) is on arXiv!
• Feb 2026 — SkillsBench, a community benchmark for LLM agent skills that I co-authored, is on arXiv!
• Dec 2025 — Our paper Deep Learning-Driven Contextual Stochastic Optimization for Real-Time Order Fulfillment (with Tinghan Ye, Shuaicheng Tong, Beste Basciftci, and Pascal Van Hentenryck) was presented at the NeurIPS 2025 ML×OR Workshop!
• Dec 2024 — Our paper Crouzeix’s conjecture, compressions of shifts, and classes of nilpotent matrices was published in Concrete Operators.
• Aug 2024 — Started my Ph.D. in Operations Research at Georgia Tech ISyE!
• May 2024 — Graduated from Bucknell University Summa Cum Laude; received The Pi Mu Epsilon Society Prize for outstanding work in mathematics.
• May 2024 — Completed my honors thesis, The Precedence-Constrained Quadratic Knapsack Problem, advised by Dr. Lucas Waddell.
• Sep 2023 — Received the INFORMS Undergraduate Scholarship and was inducted into the Tri-Alpha first-generation honor society.
• May 2023 — Inducted into the Pi Mu Epsilon (mathematics) and Omega Rho (operations research) honor societies.
• Jan 2023 — Presented our research on Crouzeix’s conjecture at the Joint Mathematics Meetings (JMM) 2023 in Boston.