Date: Wednesday, March 13th, 2024
9:00 am – 10:00 am Pacific Time
12:00 pm – 1:00 pm Eastern Time
Location: Weekly Seminar, Zoom
Title: Distributed Estimation and Social Learning in Privacy-Critical Environments
Abstract:
How can individuals exchange information to learn from each other despite their privacy needs and security concerns? For example, consider individuals deliberating a contentious topic and being concerned about divulging their private experiences or business entities who can benefit from information exchange but have privacy obligations to their clients. Efficient information aggregation and preserving individual privacy are both important desiderata but seem fundamentally at odds and hard to reconcile. We do so by controlling information leakage using rigorous statistical guarantees that are based on differential privacy (DP). Adding DP randomization noise provides communicating agents with plausible deniability with regard to their private information and their network neighborhoods. We consider two learning environments: one involving linear updates for learning best estimates and the other involving log-linear updates for choosing from a finite set of alternatives. We provide asymptotic analysis and finite-time convergence bounds subject to DP noise in both cases. Noisy information aggregation in the finite case leads to interesting tradeoffs between rejecting low-quality states and making sure all high-quality states are accepted in the algorithm output. Our results flesh out the nature of these tradeoffs between learning accuracy, communication cost, and the level and type of privacy protections that the agents are afforded. Based on joint works with Marios Papachistou; linear updates: arXiv:2306.15865; log-linear updates: arXiv:2402.08156.
Bio:
Amin Rahimian has been an assistant professor of industrial engineering at the University of Pittsburgh since 2020, where he leads the sociotechnical systems research lab. Prior to that, he was a postdoc with joint appointments at MIT Institute for Data, Systems, and Society (IDSS) and MIT Sloan School of Management. He received his PhD in Electrical and Systems Engineering from the University of Pennsylvania, and Master’s in Statistics from Wharton School. Broadly speaking his works are at the intersection of networks, data, and decision sciences, and have been published in the Proceedings of the National Academy of Sciences, Nature Human Behaviour, Nature Communications, and the Operations Research journal among others. His research interests are in applied probability, applied statistics, algorithms, decision and game theory, with applications ranging from online social networks, public health, and e-commerce to modern civilian cyberinfrastructure and future warfare. His research is currently supported by NSF, CDC, and the Department of the Army.