Optimal and Scalable
Machine Learning
Machine learning is already very powerful, but there are still so many tasks outside of its reach. How do we develop machine learning and optimization algorithms for difficult, large-scale tasks? This stream of work aims to push the boundaries on algorithm tractability while providing performance guarantees.
2024
Branch-and-Price for Prescriptive Contagion Analytics (with Jacquillat, A., Wang, K., Rame, M.). Accepted at Operations Research.
2024
Slowly Varying Regression Under Sparsity (with Bertsimas, D., Diaglakis, Lami, O. S). arXiv preprint arXiv:2102.10773 (2021). Accepted at Operations Research.
2023
Interpretable Matrix Completion: A Discrete Optimization Approach (with Bertsimas, D.). INFORMS Journal on Computing, 35(5), 952-965.
2021
Stochastic Cutting Planes for Data-Driven Optimization (with Bertsimas, D.). INFORMS Journal of Computing 34(5), 2400-2409.
2020
Fast Exact Matrix Completion: A Unified Optimization Framework for Matrix Completion (with Bertsimas, D.). Journal of Machine Learning Research, 21(231), 1-43 (2020).
2018
Scalable Holistic Linear Regression (with Bertsimas, D.). Operations Research Letters (2020).