Hossein Esfandiari

Papers

Total Citations

H-Index

About

Hossein Esfandiari is a leading researcher in the theory and practice of machine learning, with a primary focus on adaptive sequential decision making, submodular optimization, and algorithmic fairness. His work addresses fundamental challenges in designing interactive policies that can learn and act efficiently under partial information. In his highly regarded paper "Adaptivity in Adaptive Submodularity" (2019, 7 citations), Esfandiari advanced the theoretical understanding of how to balance exploration and exploitation in adaptive systems, a cornerstone problem in artificial intelligence. Beyond this, he has made significant contributions to the study of submodular functions, which are critical for problems ranging from sensor placement to viral marketing. His research is distinguished by its rigorous mathematical foundations and practical implications, often bridging the gap between theory and real-world deployment. Esfandiari’s work has been recognized for its impact on both algorithmic design and fairness constraints, making him a notable figure in the machine learning community. His insights continue to influence how researchers approach complex, sequential decision-making tasks in uncertain environments.