Iden Kalemaj

I'm a Research Scientist in Meta's Central Applied Science team since 2024. I work on privacy-preserving machine learning and contribute to the Opacus and PrivacyGuard repos. I obtained my PhD in Computer Science at Boston University in 2024, advised by Sofya Raskhodnikova. Prior to that, I studied Mathematics at Princeton University. I am based in Brooklyn, NYC. After work, I can be found at yoga or dance classes. Feel free to reach out and connect!

Email  /  Scholar  /  LinkedIn  /  Github

profile photo

Research

Observational Auditing of Label Privacy
Iden Kalemaj, Luca Melis, Maxime Boucher, Ilya Mironov, Saeed Malhoujifar
In submission

Node-Differentially Private Estimation of the Number of Connected Components
Iden Kalemaj, Sofya Raskhodnikova, Adam D. Smith, Charalampos E. Tsourakakis
Principles of Database Systems (PODS), 2023
ACM Transactions on Algorithms, 2025

Counting Distinct Elements in the Turnstile Model with Differential Privacy under Continual Observation
Palak Jain, Iden Kalemaj, Sofya Raskhodnikova, Satchit Sivakumar, Adam Smith
Neural Information Processing Systems (NeurIPS), 2023

Differentially Private Conditional Independence Testing
Iden Kalemaj, Shiva Prasad Kasiviswanathan, Aaditya Ramdas
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024

Isoperimetric Inequalities for Real-Valued Functions with Applications to Monotonicity Testing
Hadley Black, Iden Kalemaj, Sofya Raskhodnikova
International Colloquium on Automata, Languages and Programming (ICALP), 2023
Random Structures and Algorithms, 2024

Performative Prediction in a Stateful World
Gavin Brown, Shlomi Hod, Iden Kalemaj
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022

Sublinear-Time Computation in the Presence of Online Erasures
Iden Kalemaj, Sofya Raskhodnikova, Nithin Varma
Innovations in Theoretical Computer Science (ITCS), 2022
Theory of Computing, 2024

Miscellaneous