Research Interests

My primary interest is in Trustworthy Machine Learning and Data Analysis. More precisely, I study

• • Robust Learning in the Presence of Strategic Agents

  • Algorithmic Fairness in Machine Learning

  • Privacy-preserving Data Analysis

  • Algorithms for Machine Unlearning (Data Deletion)

  • Adaptive Data Analysis

Publications

*authorship is alphabetical, unless specified otherwise*

• Minimax Group Fairness in Strategic Classification [arXiv]

Emily Diana, Saeed Sharifi-Malvajerdi, Ali Vakilian.

IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2025.

• Bayesian Strategic Classification [arXiv]

Lee Cohen, Saeed Sharifi-Malvajerdi, Kevin Stangl, Ali Vakilian, Juba Ziani.

Conference on Neural Information Processing Systems (NeurIPS) 2024.

• Sequential Strategic Screening [arXiv]

Lee Cohen, Saeed Sharifi-Malvajerdi, Kevin Stangl, Ali Vakilian, Juba Ziani.

International Conference on Machine Learning (ICML) 2023.

• Multiaccurate Proxies for Downstream Fairness [arXiv]

Emily Diana, Wesley Gill, Michael Kearns, Krishnaram Kenthapadi, Aaron Roth, Saeed Sharifi-Malvajerdi.

Conference on Fairness, Accountability, and Transparency (FAccT) 2022.

• Adaptive Machine Unlearning [arXiv]

Varun Gupta, Christopher Jung, Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi, Chris Waites.

Conference on Neural Information Processing Systems (NeurIPS) 2021.

Appeared at the Workshop on Theory and Practice of Differential Privacy (TPDP) 2021.

Media Coverage: Wired Magazine

• Lexicographically Fair Learning: Algorithms and Generalization [arXiv]

Emily Diana, Wesley Gill, Ira Globus-Harris, Michael Kearns, Aaron Roth, Saeed Sharifi-Malvajerdi. 

Symposium on the Foundations of Responsible Computation (FORC) 2021.

• Descent-to-Delete: Gradient-Based Methods for Machine Unlearning [arXiv]

Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi.

International Conference on Algorithmic Learning Theory (ALT) 2021.

Appeared at the Workshop on Theory and Practice of Differential Privacy (TPDP) 2020.

• Algorithms and Learning for Fair Portfolio Design [arXiv]

Emily Diana, Travis Dick, Hadi Elzayn, Michael Kearns, Aaron Roth, Zachary Schutzman, Saeed Sharifi-Malvajerdi, Juba Ziani.

ACM Conference on Economics and Computation (EC) 2021.

• Differentially Private Call Auctions and Market Impact [arXiv]

Emily Diana, Hadi Elzayn, Michael Kearns, Aaron Roth, Saeed Sharifi-Malvajerdi, Juba Ziani.

ACM Conference on Economics and Computation (EC) 2020.

• A New Analysis of Differential Privacy's Generalization Guarantees [arXiv]

Christopher Jung, Katrina Ligett, Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi, Moshe Shenfeld.

Innovations in Theoretical Computer Science (ITCS) 2020.

Selected for a Talk.

Invited to ACM Symposium on Theory of Computation (STOC) 2021.

• Average Individual Fairness: Algorithms, Generalization and Experiments [arXiv][Github Repo]

Michael Kearns, Aaron Roth, Saeed Sharifi-Malvajerdi.

Conference on Neural Information Processing Systems (NeurIPS) 2019.

Selected for an Oral Presentation  (36/6743 submissions).

• Differentially Private Fair Learning [arXiv]

Matthew Jagielski, Michael Kearns, Jieming Mao, Alina Oprea, Aaron Roth, Saeed Sharifi-Malvajerdi, Jonathan Ullman.

International Conference on Machine Learning (ICML) 2019.

Selected for a Long Talk.

• Malaria Clearance Rate Regression: an R Software Package for a Bayesian Hierarchical Regression Model [paper][R package]

Saeed Sharifi-Malvajerdi, Feiyu Zhu, Colin B. Fogarty, Michael P. Fay, Rick M. Fairhurst, Jennifer A. Flegg, Kasia Stepniewska, Dylan S. Small.

Malaria Journal 2019 18:4.

• Analytical Studies of Fragmented-Spectrum Multi-Level OFDM-CDMA Technique in Cognitive Radio Networks [arXiv]

Farhad Akhoundi, Saeed Sharifi-Malvajerdi, Omid Poursaeed, Jawad A. Salehi.

IEEE Ubiquitous Computing, Electronics, Mobile Communication Conference (UEMCON) 2016.

Talks and Presentations

• Bayesian Strategic Classification

(Invited) INFORMS Annual Meeting, October 2024.

(Invited) NSF TRIPODS Meeting, May 2024.

Toyota Technological Institute at Chicago, April 2024.

• Machine Unlearning

(Invited) Cornell ORIE Young Researchers Workshop, 2021.

Toyota Technological Institute at Chicago, 2022.

• Adaptive Machine Unlearning

Workshop on Theory and Practice of Differential Privacy (TPDP), 2021.

• Descent-to-Delete: Gradient-Based Methods for Machine Unlearning

International Conference on Algorithmic Learning Theory (ALT), 2021.

Wharton Department of Statistics and Data Science, 2020.

• Differentially Private Call Auctions and Market Impact

INFORMS Annual Meeting, 2020.

• A New Analysis of Differential Privacy's Generalization Guarantees

Conference on Innovations in Theoretical Computer Science (ITCS), 2020.

• Average Individual Fairness: Algorithms, Generalization and Experiments

Wharton Department of Statistics and Data Science, 2019.

• Differentially Private Fair Learning

International Conference on Machine Learning (ICML), 2019.

Wharton Department of Statistics and Data Science, 2018.

• Sensitivity Analysis for the Runs Test in Matched-pair Observational Studies

Wharton Department of Statistics and Data Science, 2017.

Advising

• Roy Long (UChicago CS), TTIC summer intern working on: Fair Information Design in Strategic Classification.

Teaching

• Probability (STAT 430), Wharton Department of Statistics and Data Science, University of Pennsylvania.

• Stat Computing with R (STAT 405/705), Wharton Department of Statistics and Data Science, University of Pennsylvania.

• Introductory Statistics (STAT 111), Wharton Department of Statistics and Data Science, University of Pennsylvania.

• Digital Signal Processing, Electrical Engineering Department, Sharif University of Technology.

• Computer Architecture and Lab, Electrical Engineering Department, Sharif University of Technology.

• Communication Systems, Electrical Engineering Department, Sharif University of Technology.

• Electrical Circuits Theory, Electrical Engineering Department, Sharif University of Technology.