Research & Projects

A selection of my research and industry projects are explained in the various sections on the left. I have broadly separated my projects into areas/industries that I have felt they are chiefly concerned with. For methodologies that I feel are broadly applicable to different industries, I have put them under the General category. 

As explained on my philosophy page, I care about utilizing the interdisciplinary tools that I know (statistics, optimization, and analytics) to create impact. I work on both methodology and applications to achieve this goal, as briefly outlined below:

Methodological Research

My methodological research focus on developing new tools for prediction and evaluation in large-scale data analytics/machine learning. They mostly consists of two streams:

1. Scalable Algorithms for Data-Driven Prediction - This stream of work focuses on developing exact and approximate algorithms for NP-hard problems in machine learning and statistics that are applicable to modern data sizes, including matrix completion and sparse regression. 

2. Evaluation/Inference for Machine Learning - Another key focus of my research centers around evaluating machine learning methods. This includes both developing new algorithms for consistent inference under observational data, and also creating evaluation metrics for rigorous evaluation of black-box prescription methods. 

Applications

On applications, I have been focused on healthcare and epidemiology. During the COVID-19 pandemic, I have worked on topics ranging from advising governments on non-pharmaceutical restrictions to accelerating the Phase III trial for the J&J vaccine, contributing to saving thousands of lives around the world. Separately, I also have a continuous stream of work collaborating with Boston Children's hospital working on applying my methodological research to create and evaluate personalized treatment rules for pediatric patients. 

The full list of my papers and preprints are as followed, organized by topic:

Scalable Algorithms for Data-Driven Prediction 

Fast Exact Matrix Completion: A Unified Optimization Framework for Matrix Completion (with Bertsimas, D.). Journal of Machine Learning Research21(231), 1-43 (2020).  

Stochastic Cutting Planes for Data-Driven Optimization (with Bertsimas, D.).  INFORMS Journal of Computing (2022). Ahead of Print. 

Slowly Varying Regression Under Sparsity (with Bertsimas, D., Diaglakis, Lami, O. S). arXiv preprint arXiv:2102.10773 (2021). Submitted to Journal of Machine Learning Research

Scalable Holistic Linear Regression (with Bertsimas, D.). Operations Research Letters (2020).  

Interpretable Matrix Completion: A Discrete Optimization Approach (with Bertsimas, D.). arXiv preprint arXiv:1812.06647 (2020). Submitted to INFORMS Journal of Computing

  • Finalist, 2020 Mixed Integer Programming (MIP) Workshop Best Student Poster Competition

 

Evaluation/Inference for Machine Learning

Methodology

Experimental Evaluation of Individualized Treatment Rules (with Imai, K.). Journal of the American Statistical Association (2021): 1-41. 

Statistical Inference for Heterogeneous Treatment Effects in Randomized Experiments (with Imai, K.). Submitted to Journal of the American Statistical Association.

Robust Inference for Machine Learning with Observational Data (with Bertsimas, D., Imai, K.). In Preparation.

Pricing for Heterogeneous Products: Analytics for Ticket Reselling (with Alley, M., Biggs, M., Hariss, R., Herrmann, C., & Perakis, G.). Manufacturing & Service Operations Management (2022). Ahead of Print.   

  • Finalist, 2018 M&SOM Practice-Based Research Competition

Application: Healthcare

Data-Driven Vaccine Development with Janssen (with Bertsimas, D., Xu, J., Khan, N.) Working Paper. To Submit to Nature. 

  • Finalist, 2021 INFORMS Doing Good with Good OR Competition
  • Finalist, 2021-2022 INFORMS Edelman Competition (Winner Pending)

Forecasting COVID-19 and Analyzing the Effect of Government Interventions (with Bouardi, H. T., Lami, O. S., Trikalinos, T. A., Trichakis, N. K., & Bertsimas, D.) Operations Research (2022). Ahead of Print. 

  • Winner, 2021 INFORMS Analytics Society Innovative Applications in Analytics Award

From predictions to prescriptions: A data-driven response to COVID-19 (with Bertsimas, D., Boussioux, L., Wright, R. C., Delarue, A., Digalakis Jr, V., Jacquillat, A., ... & Nohadani, O.) Health Care Management Science, 24(2), 253-272.

  • Winner, 2020 INFORMS Health Applications Society Pierskalla Best Paper Award

Selecting Children with VUR Who are Most Likely to Benefit from Antibiotic Prophylaxis: Application of Machine Learning to RIVUR (with Wang, H. H. S., Li, M., Bertsimas, D., Estrada, C., & Caleb, N.). The Journal of Urology, 10-1097 (2020).  

Targeted Workup after Initial Febrile Urinary Tract Infection: Using a Novel Machine Learning Model to Identify Children Most Likely to Benefit from Voiding Cystourethrogram (part of Advanced Analytics Group of Pediatric Urology and ORC Personalized Medicine Group). The Journal of Urology202(1), 144-152 (2019).

Prescriptive Analytics for Reducing 30-day Hospital Readmissions after General Surgery (with Bertsimas, D.,  Paschalidis, I. C., & Wang, T.). PloS one15(9), e0238118 (2020).  

Where to locate COVID-19 mass vaccination facilities? (with Bertsimas, D., Digalakis, V., Jacquillat, A., & Previero, A.). Naval Research Logistics (NRL) (2021). 

Ensemble Forecasts of Coronavirus Disease 2019 (COVID-19) in the US (with Ray, E. L., Wattanachit, N., Niemi, J., Kanji, A. H., House, K., Cramer, E. Y., ... & COVID-19 Forecast Hub Consortium.). MedRXiv (2020). 

Evaluation of Individual and Ensemble Probabilistic Forecasts of COVID-19 Mortality in the United States (with Cramer, E. Y., Ray, E. L., Lopez, V. K., Bracher, J., Brennen, A., Castro Rivadeneira, A. J., ... & Georgescu, A.). Proceedings of the National Academy of Sciences, 119(15), e2113561119.

Short-term forecasting of COVID-19 in Germany and Poland during the second wave – a preregistered study (with Bracher, J., Wolffram, D., Deuschel, J., Gorgen, J., Ketterer, J.L., et al). Nature Communications, 12(5173), (2021). 

 

Deep Learning

Application of Duration-of-Stay Storage Assignment with Deep Neural Networks under Uncertainty (with Wolf, E., & Wintz, D.). CoRR (2020).  

  • Spotlight, 2020 International Conference on Learning Representations (ICLR)

A Hierarchy of Graph Neural Networks Based on Learnable Local Features (with Dong, M., Zhou, J., & Rush, A. M. ). arXiv preprint arXiv:1911.05256 (2019)