I am currently working on topics in fairness and diversity in Machine Learning. My current project focuses on bringing diversity into an automated admissions system. This project will help alleviate the problem of human biases in STEM admissions. I have a first author paper in submission to AAAI. A copy of the paper can be found here: https://arxiv.org/abs/1709.03441
I worked on the problem of transferring ML fairness using domain adaptation. I was able to prove theoretical bounds and produce a model which performs this transfer.
I tutor undergraduate and graduate levels of computer science using Varsity Tutor's online platform.
I worked in the Pop Lab in the Center for Bioinformatics and Computational Biology. My research focused on finding interactions in the microbiome.
I taught STEAM and electronic afterschool classes to elementary school children. I also designed new afterschool class curricula that is currently being used by Einstein By Design.
I taught a discussion section of CMSC 330 - Organization of Programming Languages.
I developed scenarios where the Internet of Things could be used in the Insurance Industry. I built a proof of concept that included everything from the IoT micro-controller to the data analysis on SAP HANA. See my finished product at https://tinyurl.com/hp4bqy3
I worked in a small team that was looking at problems in functional data analysis. I worked on developing new methods for functional data classification.
I worked on developing an intelligent Computer Go player. I was responsible for developing GPU parallel processing methods for Monte Carlo Tree Search.
I worked on the web development team on both front-end and back-end web development problems. The solutions I built were deployed to be used by the entire faculty and student body.
I researched different kinds of drafting problems and described them mathematically. I developed a greedy algorithm for the Fairy Tale card game.
Graduated Maxima Cum Laude and with General University Honors
How should a firm allocate its limited interviewing resources to select the optimal cohort of new employees from a large set of job applicants? How should that firm allocate cheap but noisy resume screenings and expensive but in-depth in-person interviews? We view this problem through the lens of combinatorial pure exploration (CPE) in the multi-armed bandit setting, where a central learning agent performs costly exploration of a set of arms before selecting a final subset with some combinatorial structure. We generalize a recent CPE algorithm to the setting where arm pulls can have different cost, but return different levels of information, and prove theoretical upper bounds for a general class of arm-pulling strategies in this new setting. We then apply our general algorithm to a real-world problem with combinatorial structure: incorporating diversity into university admissions. We take real data from admissions at one of the largest US-based computer science graduate programs and show that a simulation of our algorithm produced more diverse student cohorts at low cost to individual student quality, and does so by spending comparable budget to the current admissions process at that university.
I co-presented a talk at the DEF CON Biohacking conference. The talk focused on breakthroughs in computational biology and how the information security community could help extend current research efforts.
I co-presented a talk at BSidesLV 2016 that focused on the intersection of Computational Biology and Information Security. https://youtu.be/lgWFMrwgzuQ
Paper published in the Journal of Computing Sciences in Colleges