We work on responsible and deployable machine learning and natural language processing in shifting environments. To achieve this, we build

1. Robust methods for learning from data and labels that are are biased, missing, or noisy

2. Models that generalize and adapt to ever-shifting distributions and requirements

3. Tools to make models meet crucial human requirements like equity, updatability, and explainability

We are particularly interested in healthcare environments and medical applications and have many ongoing efforts and collaborations on NLP for Oncology, modeling EHR time series, and detecting adverse outcomes in mental health, diabetes, and in-hospital acquired infections.

Mentoring Philosophy

While our group studies impactful, fast-paced, and exciting problems, we emphasize healthy work-life balance and general wellbeing to maintain sustainable quality of life.

I aim to broaden participation in machine learning research in all aspects: folks from all walks of life are welcome and I do my best to accommodate everyone's situation.

Successful research should be fun to conduct and involve diving deep into details. To facilitate this, we work together to define concrete problems we are both excited about.

I encourage and seek independence at all stages of your degree.

Supervision style: I meet each student 1:1 for 1 hour per week. This meeting is student-led and often focuses on research updates and feedback on research. I also try to be available as much as possible for paper-writing and other support.

A big component of doing a PhD is self-discovery, so I encourage students to try new things and read broadly. One way I facilitate this is through a weekly paper-reading group.