About me

I am a postdoc at MIT in the Computer Science and Artificial Intelligence Laboratory (CSAIL).

My research focuses on machine learning, data mining, time series, applications to healthcare, NLP, and fairness in AI systems.

At MIT, I work with Professor Marzyeh Ghassemi as a member of the HealthyML lab.

Research

I build machine learning and data mining systems to support time-sensitive decision making without perpetuating societal biases. The projects that excite me the most: (1) provide robust models of ongoing systems, often through partially-observed time series, (2) defend users from machine bias, and (3) have impact through real-world deployment.

Some of my recent projects include:

  • ToxiGen, a language model-generated dataset for detecting implicitly toxic language that targets minority groups.
  • Systems for learning to stop and classify ongoing time series early in time-sensitive domains (see KDD'19 and KDD'20 papers).
  • Explaining black-box models for time series and natural language processing (see CIKM'21 and ACL'20 papers).
  • Methods for recovering models of annotators' labeling behavior from machine learning datasets (see AAAI'22 and SDM'22 papers).

For more details, please visit my full list of publications.

What’s New?

History

Before MIT, I did my PhD in Data Science at Worcester Polytechnic Institute, advised by Professors Elke Rundensteiner and Xiangnan Kong. Before that, I graduated from SUNY Geneseo in 2016 with a B.A. in Applied Mathematics.

Misc

Outside of research, I enjoy bouldering, biking, books (science fiction/science fact), birding, juggling, and playing guitar. I also spent a summer living at BioSphere 2 in rural Arizona.