I am a Ph.D. candidate in the Electrical Engineering and Computer Science Department at MIT. I am fortunate to work with Professor Asuman Ozdaglar and Professor Daron Acemoglu. My research interests lie in the span of machine learning theory, economics and computation, game theory, optimization, and privacy. In particular, I work toward understanding different aspects and challenges in deploying machine learning algorithms, from convergence and performance guarantees to their interactions with strategic users and potential societal considerations.
My research is currently supported by the Apple Scholars in AI/ML PhD fellowship. I have also been the recipient of the MathWorks Engineering Fellowship and Siebel Scholarship.
I spent summer 2020 as a research intern at Apple ML Privacy team. Before coming to MIT, I earned a dual B.Sc. degree in Electrical Engineering and Mathematics from Sharif University of Technology.
Here are links to my Google Scholar and my CV.
Recent News
- May 2023: Presented our work on privacy guarantees and platforms behavior at the Marketplace Innovation Workshop.
- January 2023: New paper out: How Good Are Privacy Guarantees? Data Sharing, Privacy Preservation, and Platform Behavior
- December 2022: Attended the NeurIPS 2022 conference to present our paper on Bridging Central and Local Differential Privacy in Data Acquisition Mechanisms!
- October 2022: I presented the following two works at 2022 INFORMS Annual Meeting:
- Privacy Costs Of Strategic Data Sharing: Implications Of Shuffling
- with Daron Acemoglu, Ali Makhdoumi, Azarakhsh Malekian, and Asuman Ozdaglar.
- Optimal And Differentially Private Data Acquisition: Central And Local Mechanisms
- with Ali Makhdoumi, Azarakhsh Malekian, and Asuman Ozdaglar.
- Privacy Costs Of Strategic Data Sharing: Implications Of Shuffling
- October 2022: I will present my work on privacy mechanisms for data markets at the Cornell ORIE Young Researchers Workshop.
- September 2022: Attended the Allerton Conference to present the following two works:
- Optimal Private Data Acquisition: Central and Local Differential Privacy
- Personalized Federated Learning: A Meta-learning Approach
- September 2022: Our paper on Bridging Central and Local Differential Privacy in Data Acquisition Mechanisms just got accepted to NeurIPS 2022!
- July 2022: Our paper on robust accelerated gradient methods for distributed optimization is accepted for publication in the Journal of Machine Learning Research (JMLR)!
- July 2022: Presented our work on differentially private data acquisition at two more workshops:
- ICML workshop on Theory and Practice of Differential Privacy (TPDP), Baltimore, USA.
- The workshop on Differential Privacy and Statistical Data Analysis, The Fields Institute for Research in Mathematical Sciences, University of Toronto.
- July 2022: Attended the Economics and Computation (EC’22) conference in Boulder, Colorado, to present our accepted paper on differentially private data acquisition which will appear as an extended abstract [Video].
- June 2022: Received a minor revision decision from the Operations Research journal for our paper titled “Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms”.
- June 2022: Presented our work on differentially private data acquisition at the INFORMS Revenue Management and Pricing (RM&P) Section Conference & Manufacturing and Service Operations Management Conference (MSOM).
- May 2022: Presented our work on differentially private data acquisition at the seventh Marketplace Innovation Workshop.