Hello!
I am a Phd Candidate in computer science advised by
Professor Avrim Blum
at the Toyota Technological Institute at Chicago.
My research focuses on theory and algorithms for learning with data corruptions, adversaries, and fairness requirements.
Some of my work includes considering group fairness and biased data FORC 2020,
fairness and screening problems FAACT 2022,
strategic classification ICML 2023, adversarial robustness AISTATS 2024 , and fair-ERM with malicious noise AISTATS 2024.
During Winter 2024, I will be interning at SPR/Intel labs, working on adversarial robustness with Marius Arvinte.
I interned at J.P. Morgan AI (NYC) during Summer 2023, on the explainable AI team, working with Margarita Boyarskaya on actionable recourse.
I have served as a reviewer for ITCS, FAACT, and ICALP.
Generally speaking, I am most interested in formally modelling problems in order to pin down complex behavior and ensure reliable and beneficial systems.
My email is my first name at ttic dot edu.
News:
Publications:
Here is my ArXiv and my google scholar.
Talks:
- Sequential Strategic Screening, IDEAL: Workshop on Machine Learning, Interpretability, and Logic, Chicago (USA), April 2023
- Multi Stage Screening: Enforcing Fairness and Efficiency in a Pre-existing Pipeline, TOC 4 Fairness , online, June 2022, (video)
- Fairness in Machine Learning in Two Contexts: Biased Data and Pipelines, UIC Computer Science Theory Seminar , Chicago (USA), March 2022
- Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?, Foundations of Responsible Computing 2020 , online, May 2020, (video) May 2020
Teaching Experience:
Awards:
- TTIC Outstanding TA Award, 2019