Keegan W. Harris
Office: GHC 8021
Carnegie Mellon University
5000 Forbes Avenue
Pittsburgh, PA 15213
Email: keeganh [at] cs.cmu.edu
Hello! I am a third-year Ph.D. student in the School of
Computer Science at Carnegie Mellon University. I am fortunate to be advised by
Nina Balcan and
Steven Wu, and supported by the
Before coming to CMU, I graduated summa cum laude from
Penn State University
with Bachelor of Science degrees in
Computer Science and
I am interested in topics at the intersection of machine learning, econometrics, and algorithmic game theory.
Specifically, my goal is to develop principled algorithms for modern data-driven decision-making.
To this end, my research has been focused on three (often interleaved) areas:
- Learning and decision-making using panel data: In settings such as e-commerce, content recommendation systems, and clinical trials,
one often observes repeated, noisy, measurements from a collection of individuals over a period of time. Such settings are ubiquitous in today's
digital world, and are often referred to as panel data settings.
I am interested in leveraging the temporal structure and similarity between individuals typically present in panel data
to design better algorithms for decision-making in real-world settings.
- Algorithmic decision-making under incentives: When algorithmic assessment tools are used in high-stakes domains such as
lending, education, or employment, decision-subjects have an incentive to modify their input to the algorithm in
order to receive a more desirable outcome. As a result, machine learning systems deployed in these settings need to take
such strategic interactions into consideration in order to make reliable predictions (and decisions).
To this end, I have investigated the effects of incomplete information, causal learning, and repeated interactions in the
domain of algorithmic decision-making under incentives.
- Learning in non-stationary environments: While classical machine learning focuses on learning a single model for a single task using data from a stationary distribution,
the real world is often non-stationary and requires reasoning about many different-but-related tasks, often with just a small amount of data from each.
For example, in online advertising auctions, the advertiser’s value for different keywords adapts based on current marketing trends.
In online marketplaces, the price consumers are willing to pay for different products varies based on the current economic outlook.
My research in this area has been focused on developing meta-learning algorithms for decision-making with provable performance guarantees,
which are capable of operating under partial feedback and in the presence of other strategic agents.
Feel free to reach out if you'd like to chat about research or graduate school admissions in computer science. The best way to reach me is
at the email address listed above.
- February 2023: I was recognized as a top reviewer for AISTATS 2023!
- January 2023: One paper accepted to ICLR!
- December 2022: I received my Master's degree in Machine Learning!
- September 2022: One paper accepted to NeurIPS!
- August 2022: I am co-organizing the SIGecom Seminar Series for the fall 2022 semester! Check out our website here.
- May 2022: One paper accepted to ICML!
- April 2022: I was awarded the NDSEG Fellowship!
- April 2022: One paper accepted to FORC 2022!
Excited to attend my first in-person conference!
- March 2022: Our work was selected for two oral presentations at the
Learning with Strategic Agents Workshop at AAMAS 2022!
- December 2021: I attended NeurIPS (virtually). Here's a
link to my oral presentation at the WHMD workshop.
- October 2021: Our work on Bayesian Persuasion for Algorithmic Recourse was selected for an oral presentation at the
Workshop on Human and Machine Decisions at NeurIPS 2021!
- September 2021: One paper accepted to NeurIPS!
- August 2021: I wrote a blog post for CMU's Machine Learning Blog! Check it out
- July 2021: Our work on Strategic Instrumental Variable Regression was selected for a spotlight presentation
at the Algorithmic Recourse Workshop at ICML 2021! View a recording of my talk
- June 2021: I presented our work on Stateful Strategic Regression at FORC 2021! View my short talk
here and my long talk