Mahbod Majid

I am a PhD student at MIT, working under the supervision of Ankur Moitra. I studied my master’s in the algorithms and complexity group at the University of Waterloo where I was fortunate to be advised by Gautam Kamath.

Google Scholar / DBLP / arXiv / Github / Twitter

publications

Sample-Optimal Private Regression in Polynomial Time
Prashanti Anderson, Ainesh Bakshi, Mahbod Majid, Stefan Tiegel.
STOC 2025. arxiv

On the Consistent Recovery of Joint Distributions from Conditionals
Mahbod Majid*, Rattana Pukdee*, Vishwajeet Agrawal*, Burak Varıcı, Pradeep Kumar Ravikumar.
AISTATS 2025.

Private Mean Estimation with Person-Level Differential Privacy
Sushant Agarwal, Gautam Kamath, Mahbod Majid, Argyris Mouzakis, Rose Silver, Jonathan Ullman.
SODA 2025. arxiv

Sample-Efficient Private Learning of Mixtures of Gaussians
Hassan Ashtiani, Mahbod Majid, Shyam Narayanan.
NeurIPS 2024 (Spotlight Presentation) arxiv

Robustness Implies Privacy in Statistical Estimation.
Samuel B. Hopkins, Gautam Kamath, Mahbod Majid, Shyam Narayanan.
STOC 2023. arxiv
Presented at TPDP 2023 (Oral Presentation).

Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism.
Samuel B. Hopkins, Gautam Kamath, Mahbod Majid.
STOC 2022. arxiv video
Presented at FORC 2022, non-archival track.
Presented at TPDP 2022.

contact

mahbod at mit.edu