Research and Publications

Interests

My research interests are at the interface between convex optimization and statistical machine learning. Specifically, I am interested in theoretical and practical issues involving first-order methods in convex optimization, their connections to algorithms in machine learning/statistics, and applications thereof. More broadly, I am interested in methodology and applications of large-scale optimization problems, often under uncertainty, and where data plays a key role in driving formulations and computations.

Here is a link to my Google Scholar profile.

Publications and Working Papers

  • New Methods for Regularization Path Optimization via Differential Equations, with Heyuan Liu, NeurIPS 2019 Workshop on Beyond First Order Methods in Machine Learning, accepted. [pdf]

  • Stochastic In-Face Frank-Wolfe Methods for Non-Convex Optimization and Sparse Neural Network Training, with Alfonso Lobos and Nathan Vermeersch, working paper. [arXiv]

  • Generalization Bounds in the Predict-then-Optimize Framework, with Othman El Balghiti, Adam N. Elmachtoub, and Ambuj Tewari, Advances in Neural Information Processing Systems (NeurIPS) 32, pp. 14389-14398, 2019. [arXiv]

  • Condition Number Analysis of Logistic Regression, and its Implications for Standard First-Order Solution Methods, with Robert M. Freund and Rahul Mazumder, working paper. [arXiv]

  • Optimal Bidding, Allocation and Budget Spending for a Demand Side Platform Under Many Auction Types, with Alfonso Lobos, Zheng Wen, and Kuang-chih Lee, working paper.

    • Preliminary extended abstract version was presented at the 2018 AdKDD & TargetAd Workshop at KDD, London, United Kingdom, 2018. [arXiv]

    • Winner of the Best Student Paper Prize (Alfonso Lobos) at the 2018 AdKDD & TargetAd Workshop at KDD, London, United Kingdom, 2018.

  • Smart “Predict, then Optimize,” with Adam N. Elmachtoub, Management Science, forthcoming. [arXiv]

    • 1st place in the 2020 INFORMS Junior Faculty Interest Group (JFIG) Paper Competition.

  • Profit Maximization for Online Advertising Demand-Side Platforms, with Alfonso Lobos, Zheng Wen, and Kuang-chih Lee, 2017 AdKDD & TargetAd Workshop at KDD 2017, Halifax, Canada. [pdf] [arXiv]

  • An Extended Frank-Wolfe Method with “In-Face” Directions, and its Application to Low-Rank Matrix Completion, with Robert M. Freund and Rahul Mazumder, SIAM Journal on Optimization 27 (1), pp. 319-346, 2017. [pdf] [arXiv]

  • A New Perspective on Boosting in Linear Regression via Subgradient Optimization and Relatives, with Robert M. Freund and Rahul Mazumder, The Annals of Statistics 45 (6), pp. 2328-2364, 2017. [pdf] [arXiv]

    • Selected to be presented in the Annals of Statistics Special Invited Session at JSM 2017, which features the four best papers accepted to The Annals of Statistics in the previous two years.

    • Winner of the 2015 INFORMS Optimization Society Student Paper Prize.

    • Short article appeared in the INFORMS Optimization Society Newsletter.

  • New Analysis and Results for the Frank-Wolfe Method, with Robert M. Freund, Mathematical Programming 155 (1), pp. 199-230, 2016. [pdf] [arXiv]

  • AdaBoost and Forward Stagewise Regression are First-Order Convex Optimization Methods, with Robert M. Freund and Rahul Mazumder, MIT Operations Research Center working paper OR 397-14 (preliminary unpublished manuscript). [pdf] [arXiv]

Ph.D. Students

  • Alfonso Lobos (expected 2020)

  • Heyuan Liu (expected 2022)