Samuel Dooley

I am a third year graduate student that University of Maryland. I'm motivated by work that improves, studies, or changes how technology is used. Together with my advisor, John P. Dickerson, I am looking at various mechanism design questions in multi-armed bandits and labor markets. With Philip Resnik, I am applying these theoretical advances to mental health risk assessment. I also study how public libraries provide security and privacy on their public computers with Michelle Mazurek, Rachel Greenstadt, and Nora McDonald. Before graduate school, I worked on vision problems in overhead imagery.

I have a Master's in Statistics from Georege Washington University, and a Bachelor's in Mathematics from University of Chicago.

Papers

Health Care

Samuel Dooley, Candice Schumann, Han-Chin Shing, John P Dickerson, and Philip Resnik. A multi-stage human-machine framework for mental health risk assessment. Under Submission, 2020.

Samuel Dooley, Candice Schumann, Han-Chin Shing, John P Dickerson, and Philip Resnik. Sequential decision making in resource constrained global health settings. ML For Global Health at ICML-20, 2020.

Duncan C McElfresh, Samuel Dooley, Yuan Cui, Kendra Griesman, Weiqin Wang, Tyler Will, Neil Sehgal, and John P Dickerson. Can an algorithm be my healthcare proxy? Workshop on Health Intelligence at AAAI-20, 2020. [Link.]

Machine Learning

Samuel Dooley and John P Dickerson. Global best arm identification in contextual bandits. Working Paper, 2020.

Vedant Nanda*, Samuel Dooley*, Sahil Singla, Soheil Feizi, and John P Dickerson. Fairness through robustness: Investigating robustness disparity in deep learning. Under Submission, 2020. [Link.]

Markets

Marina Knittel, Samuel Dooley, and John P Dickerson. The binary amliate matching problem: approval-based matching with applicant-employer relations. Under Submission, 2020.

Kevin Kuo, Anthony Ostuni, Elizabeth Horishny, Michael J Curry, Samuel Dooley, Ping-yeh Chiang, Tom Goldstein, and John P Dickerson. Proportionnet: Balancing fairness and revenue for auction design with deep learning. Under Submission. arXiv preprint arXiv:2010.06398, 2020. [Link.]

Libraries

Samuel Dooley, Michael Rosenberg, Elliott Sloate, Sungbok Shin, and Michelle Mazurek. Libraries' approaches to the security of public computers. 5th Workshop on Inclusive Privacy and Security at SOUPS-20, 2020. [Link.]

Computer Vision for Overhead Imagery

Darius Lam, Richard Kuzma, Kevin McGee, Samuel Dooley, Michael Laielli, Matthew Klaric, Yaroslav Bulatov, and Brendan McCord. xview: Objects in context in overhead imagery. ML for the Developing World at NeurIPS-17, 2018. [Link.]

Eliza Mace, Keith Manville, Monica Barbu-McInnis, Michael Laielli, Matthew Klaric, and Samuel Dooley. Overhead detection: Beyond 8-bits and rgb. Naval Applications of Machine Learning, 2018. [Link.]