I am an Assistant Professor at the Department of Operations Research and Financial Engineering at Princeton University. I am an associate faculty with Department of Electrical and Computer Engineering, the Center for Statistics and Machine Learning, and the Robotics at Princeton initiative. I am also a fellow at Princeton Whitman college.
My research lies at the interface of mathematical optimization, machine learning, and optimal control. It focuses on data-driven computational tools to make decisions in highly dynamic and uncertain environments.
New preprint Differentiable Cutting-plane Layers for Mixed-integer Linear Optimization led by Gabriele Dragotto and Stefan Clarke, and in collaboration with Jaime Fernandez Fisac! See thread on X! Differentiable optimization 🤝 cutting plane algorithms!
New preprint GeNIOS: an (almost) second-order operator-splitting solver for large-scale convex optimization led by Theo Diamandis and in collaboration with with Zach Frangella, Shipu Zhao, and Madeleine Udell. Check out the Julia code!
New preprint Learning to Warm-Start Fixed-Point Optimization Algorithms! We introduce a new learning framework to warm-start fixed-point optimizers, with great computation savings and generalization guarantees. Check out the code! Joint work with collaborators Georgina Hall, Brandon Amos, and led by my student Rajiv Sambharya.
It was great to attend the International Conference on Stochastic Programming in UC Davis. Irina Wang gave a talk on Mean Robust Optimization and I gave one on Learning for Robust Optimization.
Amit Solomon just joined our group as a Research Software Engineer (RSE)! He will help us build great software packages to disseminate our work on numerical optimization. Amit is part of a new initiative by Princeton Research Computing to greatly expand the number of RSEs.
It was great to attend L4DC! My student Rajiv Sambharya presented a poster on End-to-End Learning to Warm-Start for Real-Time Quadratic Optimization.
Thrilled to receive the NSF CAREER Award for the project entitled Learning for Real-Time Embedded Optimization!
Our paper End-to-End Learning to Warm-Start for Real-Time Quadratic Optimization has been accepted to L4DC
New preprint The Benefit of Uncertainty Coupling in Robust and Adaptive Robust Optimization in collaboration with Liangyuan Na and Dimitris Bertsimas.
New preprint On the (linear) convergence of Generalized Newton Inexact ADMM. Great collaboration with Zach Frangella, Shipu Zhao, Theo Diamandis, and Madeleine Udell.
New preprint Equitable Data-Driven Resource Allocation to Fight the Opioid Epidemic: A Mixed-Integer Optimization Approach, in collaboration with my senior thesis student Joyce Luo (now at MIT ORC).
New preprint End-to-End Learning to Warm-Start for Real-Time Quadratic Optimization, joint with collaborators Georgina Hall, Brandon Amos, and my student Rajiv Sambharya.
I gave a talk on Learning for Fast and Robust Real-Time Optimization at UC Berkeley Mechanical Engineering Seminar. Thanks Francesco Borrelli for the invitation!
I gave a talk on Real-Time Decision-Making for Clean and Resilient Energy Systems at the ISSNAF Franco Strazzabosco Award Symposium. Video here.
I gave a talk on Mean Robust Optimization at the Future of Analytics and Operations Research workshop at the INFORMS Annual Meeting.
Stefan Clarke (PhD) and Cole Becker (MSE) joined our group as graduate students.
New preprint Mean Robust Optimization in collaboration with Bart Van Parys and my students Irina Wang and Cole Becker.
I gave a talk on Real-time decision-making via data-driven optimization at Politecnico di Milano at the DEIB Department Seminar. First time I was there after 10 years! Thanks Maria Prandini for the invitation!
Our proposal for an ORFE Research Software Engineer was selected for funding!
Cole Becker won the Princeton SEAS Mueller Prize and the John Ogden Bigelow Jr. Prize in Electrical Engineering.
I gave a talk on Real-time decision-making via data-driven optimization at the Cornell ORIE Seminar. Thanks Andrea Lodi for the invitation!
I gave a talk on Real-time decision-making via data-driven optimization at the NASA JPL Multi-Agent Tech Talks. Thanks Federico Rossi for the invitation!
Our paper Embedded Code Generation with CVXPY was accepted for publication in IEEE Control Systems Letters. It will be presented at IEEE CDC 2022.
I received the Princeton SEAS Innovation Award for the proposal "Learning Task-specific Optimizers for Real-time Autonomous Systems”!
Our paper Online mixed-integer optimization in milliseconds was accepted for publication in INFORMS Journal on Computing.
I served in the program committee of the 4th L4DC conference.
Our paper CoCo: Online Mixed-Integer Control via Supervised Learning was accepted for publication in Robotics and Automation Letters!
I gave a talk on Accelerating quadratic optimization with reinforcement learning at the INFORMS Annual Meeting.
I received the 250th Anniversary Fund for Innovation for Undergraduate Education for redesigning ORF307.
I gave a talk on Real-time decision-making via data-driven optimization at the Joint Princeton Robotics and Optimization Seminar (video).
Our paper Machine Learning for Real-Time Heart Disease Prediction was accepted for publication in IEEE Journal of Biomedical and Health Informatics.
I started teaching the undergraduate optimization class ORF307.
Rajiv Sambharya joined our group as a graduate student.
I served in the program committee of the 3rd L4DC conference.
I gave a talk on Real-time decision-making via data-driven optimization at the Raytheon Technologies Research Center. Thanks Alessandro Pinto for the invitation.
I started teaching the graduate optimization class ORF522.
I started organizing the Princeton Optimization Seminar.