I'm currently a postdoc at the Univeristy of Tubingen supervised by Ulrike von Luxburg. Previously, I completed my Phd at UC San Diego where I was fortunate to be co-advised by Kamalika Chaudhuri and Sanjoy Dasgupta. I'm broadly interested in various theoretical topics that fall under the umbrella of Trustworthy Machine Learning. Recently, I've been interested in studying basic problems in explainability. I've previously worked in adversarial robustness as well as online k-means clustering. I also like math, in which I receieved a B.S. from MIT in 2016.
Preprints
- Robi Bhattacharjee, Nick Rittler, and Kamalika Chaudhuri. "Beyond Discrepancy: A Closer Look at the Theory of Distribution Shift" In Submission
Publications
- Robi Bhattacharjee and Ulrike von Luxburg. "Auditing Local Explanations is Hard." Neurips 2024
- Robi Bhattacharjee, Sanjoy Dasgupta, and Kamalika Chaudhuri. "Data-Copying in Generative Models: A Formal Framework." ICML 2023
- Robi Bhattacharjee, Max Hopkins, Akash Kumar, Hantao Yu, and Kamalika Chaudhuri. "Robust Empirical Risk Minimization with Tolerance" ALT 2023
- Robi Bhattacharjee, Jacob Imola, Michal Moshkovitz, and Sanjoy Dasgupta. "Online k-means Clustering on Arbitrary Data Streams." ALT 2023
- Robi Bhattacharjee and Gaurav Mahajan. "Learning what to remember." ALT 2022
- Robi Bhattacharjee and Kamalika Chaudhuri. "Consistent Non-Parametric Methods for Maximizing Robustness." Neurips 2021
- Robi Bhattacharjeee, Somesh Jha, and Kamalika Chaudhuri. "Sample Complexity of Adversarially Robust Linear Classification on Separated Data." ICML 2021
- Robi Bhattacharjee and Michal Moshkovitz. "No-substitution k-means Clustering with Adversarial Order." ALT 2021.
- Robi Bhattacharjee and Kamalika Chaudhuri. "When are Non-Parametric Methods Robust?" ICML 2020.
- Robi Bhattacharjee and Sanjoy Dasgupta. "What relations are reliably embeddable in Euclidean space?." ALT 2020.