Robi Bhattacharjee
Education
University of California, San Diego
PhD in Computer Science
Advised by Kamalika Chaudhuri and Sanjoy Dasgupta.
Massachusetts Institute of Technology
Bachelor of Science, General Mathematics
Work Experience
Postdoctoral Researcher
University of Tübingen — Tübingen, Germany
Supervised by Ulrike von Luxburg. Conducting research in theoretical machine learning.
PhD Student, Graduate Research Assistant
UC San Diego — San Diego, CA
Conducted research in adversarial robustness, clustering, and trustworthy machine learning under Kamalika Chaudhuri and Sanjoy Dasgupta.
Assistant Trader
Five Rings Capital — New York, NY
Developed automated trading strategies and coded simulations on historical market data.
Research Intern
Jane Street Capital — New York, NY
Worked on trading strategies and statistical tools for improving them.
Software Engineering Intern
Google — Mountain View, CA
Studied the effect of over- and under-sampling to resolve class imbalance for fraud detection.
Trading/Research Intern
Jane Street Capital — New York, NY
Worked on trading strategies and participated in mock trading exercises.
Teaching
Teaching Assistant, Seminar “Explainable Machine Learning”
University of Tübingen
Co-led by Ulrike von Luxburg, Gunnar Konig, Sebastian Bordt, and Robi Bhattacharjee. Delivered lectures (e.g. on LIME/SHAP), guided student presentations, and organized the seminar schedule.
Teaching Assistant, CSE 251B (Graduate Machine Learning)
UC San Diego
Led discussion sections, held office hours, graded assignments and exams.
Teaching Assistant, CSE 251B (Graduate Machine Learning)
UC San Diego
Led discussion sections, held office hours, graded assignments and exams.
Supervision
Clara Groethans
Master’s Student, University of Tübingen
Thesis: Understanding the Interplay between Model Complexity and Explanation Quality: Measuring Local Fidelity.
Harald Kugler
Master’s Student, University of Tübingen
Thesis: Towards a Reliable and Scalable Data-Copying Detection Algorithm Using Random Projections.
Publications
- Robi Bhattacharjee, Geelon So, and Sanjoy Dasgupta. “Consistency of the kn-nearest neighbor rule under adaptive sampling.” NeurIPS 2025.
- Robi Bhattacharjee, Karolin Frohnapfel, and Ulrike von Luxburg. “How to Safely Discard Features Based on Aggregate SHAP Values.” COLT 2025.
- 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 Bhattacharjee, 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.
Preprints / In Submission
- Eric Günther, Balázs Szabados, Robi Bhattacharjee, Sebastian Bordt, and Ulrike von Luxburg. “Informative Post-Hoc Explanations Only Exist for Simple Functions.” arXiv preprint, 2025.
- Robi Bhattacharjee, Nick Rittler, and Kamalika Chaudhuri. “Beyond Discrepancy: A Closer Look at the Theory of Distribution Shift.” In submission.
Talks
- “How to Safely Discard Features Based on Aggregate SHAP Values.” COLT 2025.
- “Robust Empirical Risk Minimization with Tolerance.” ALT 2023.
- “Online k-means Clustering on Arbitrary Data Streams.” ALT 2023.
- “Learning What to Remember.” ALT 2022.
- “No-substitution k-means Clustering with Adversarial Order.” ALT 2021.
- “When are Non-Parametric Methods Robust?” ICML 2020.
- “What Relations are Reliably Embeddable in Euclidean Space?” ALT 2020.
Honors and Awards
- Honorable Mention on the William Lowell Putnam Examination (2012, 2013).
- 9th place individual nationally in the American Regional Mathematics Competition.
- Participant of the Math Olympiad Summer Program (2010).
- USAMO qualifier 2009–2012 (ranked 26th in the nation in 2012).
Service
- Reviewer, NeurIPS 2025.
- Reviewer, ICLR 2025.
- Reviewer, ALT 2025.
- Reviewer, ICML 2025.
- Reviewer, NeurIPS 2024.
- Reviewer, ICML 2024.
- Reviewer, ICML 2023.
- Reviewer, ICML 2022.
- Reviewer, ICML 2021.
- Reviewer, JMLR 2021.
- Reviewer, AISTATS 2020.
- Mentor for UCSD Graduate Women in Computing (Fall 2020 – Winter 2021).
- Geometry teacher for MISE foundation (Winter 2020 – Summer 2021).