I am an Assistant Professor in Computer Science at the University of Iowa. Previously, I was a TRIPODS Postdoctoral Research Fellow at the University of Illinois at Urbana Champaign, working with Prof. R. Srikant as my Postdoc advisor. I received my B.Sc. from the Sharif University of Technology, Iran, in Mathematics as well as Electrical Engineering. I hold an M.Sc. in Electrical Engineering and a M.Sc. in Mathematics from the University of Michigan. I received my Ph.D. in Electrical Engineering in Winter 2020, for which I was awarded the Rackham Predoctoral Fellowship for an outstanding dissertation. I was fortunate to have Prof. Mingyan Liu and Prof. Vijay Subramanian as my Ph.D. advisors.
My research so far spans two areas: (1) reinforcement learning and MDPs, and (2) computationally efficient algorithms for learning and economics in societal systems modeled as random graphs. (1) I study data-driven algorithms modeling the underlying environment as an MDP. My main focus is to develop robust algorithms against distributional shifts and model uncertainties. (2) I study the impact of structural properties of real-world networks on interactions of individuals with fixed behavior, modeling the networks as a family of parameterized random graphs. My main focus is to understand and predict the results of interactions when the underlying parameter, and hence the structural properties of the network, varies.
My research interests are Markov decision processes, reinforcement learning, and random graph models for economics, learning, and computation.
12/2025 - I was selected as a Champion for Student Success.
12/2025 - Our paper titled "A Theoretical Model of Flock Formation to Understand Trade-offs between Cooperation and Competition" has been accepted in Ecosphere.
10/2025 - Our paper titled "On the Convergence of Modified Policy Iteration in Risk-Sensitive Exponential Cost Markov Decision Processes" has been accepted in Operations Research.
05/2025 - Gauri Joshi, Srinivas Shakkottai, and I have organized the SC&RL workshop in conjunction with ACM SIGMETRICS 2025.
05/2025 - Our paper titled "The Planted Spanning Tree Problems: Exact Overlap Characterization via Local Weak Convergence" has been accepted in COLT 2025.
05/2025 - Our paper titled "Online Learning in Risk Sensitive constrained MDP" has been accepted in ICML 2025.
02/2025 - I had the privilege of presenting one of my recent works as an invited speaker at ITA 2025.
I am seeking to hire one PhD students in theoretical reinforcement learning and one PhD student in the limiting behavior of random graph models.
For the reinforcement learning positions, applicants should have a strong background in foundational topics such as probability, optimization, and learning theory. For the random graph position, applicants should have a strong mathematical background in probability, and combinatorics.
If you are interested, please email me and include in the subject line which of the two areas you are most interested in.
Mehrdad Moharrami*, Arnob Ghosh*, "Online Learning in Risk Sensitive constrained MDP", ICML 2025.
Yashaswini Murthy, Mehrdad Moharrami, R. Srikant, "On the Convergence of Modified Policy Iteration in Risk Sensitive Exponential Cost Markov Decision Processes", Operations. Research
Yashaswini Murthy, Mehrdad Moharrami, R. Srikant, "Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms", NeurIPS 2023.
Yashaswini Murthy, Mehrdad Moharrami, R. Srikant, "Modified Policy Iteration for Exponential Cost Risk Sensitive MDPs", L4DC 2023.
Mehrdad Moharrami, Yashaswini Murthy, Arghyadip Roy, R. Srikant, "A Policy Gradient Algorithm for the Risk-Sensitive Exponential Cost MDP", Mathematics of Operation Research.
Saghar Adler, Mehrdad Moharrami, Vijay Subramanian, "Learning a Discrete Set of Optimal Allocation Rules in Queueing Systems with Unknown Service Rates", Under Review.
Chenlan Wang, Mehrdad Moharrami, Shane G. DuBay, Mingyan Liu, "A Theoretical Model of Flock Formation to Understand Trade-offs between Cooperation and Competition", Ecosphere.
Mehrdad Moharrami, Cristopher Moore, Jiaming Xu, "The Planted Spanning Tree Problems: Exact Overlap Characterization via Local Weak Convergence", COLT 2025.
Mehrdad Moharrami, Vijay Subramanian, Mingyan Liu, Rajesh Sundaresan, "The Erlang Weighted Tree, A New Branching Process'', Random Structures and Algorithms.
Mehrdad Moharrami, Cristopher Moore, Jiaming Xu, "The Planted Matching Problem: Phase Transitions and Exact Results", Annals of Applied Probability.
Mehrdad Moharrami, Vijay Subramanian, Mingyan Liu, Marc Lelarge, "Impact of Community Structure on Cascades", EC 2016.
Nouman Khan, Mehrdad Moharrami, Vijay Subramanian, "Rarest-First with Probabilistic-Mode-Suppression", IEEE Transactions on Information Theory.
Nouman Khan, Mehrdad Moharrami, Vijay Subramanian, "Stable and Efficient Piece-Selection in Multiple Swarm BitTorrent-like Peer-to-Peer Networks", INFOCOM 2020.
Chenlan Wang, Mehrdad Moharrami, Kun Jin, David Kempe, P. Jeffrey Brantingham, Mingyan Liu, "Structural Stability of a Family of Group Formation Games", IEEE Transactions on Network Science.
Nouman Khan, Kangle Mu, Mehrdad Moharrami, Vijay Subramanian, "Backward and Forward Inference in Interacting Independent-Cascade Processes: A Scalable and Convergent Message-Passing Approach", CoRR 2023.
Mehrdad Moharrami, Ahmad Fallahpour, Hamzeh Beyranvand, Jawad A. Salehi, "Resource Allocation and Multicast Routing in Elastic Optical Networks", IEEE Transactions on Communications.
Champion for Student Success, University of IOWA, 2025
Wolfram Summer School Fellowship, Bentley University, 2023
Rackham Predoctoral Fellowship, University of Michigan, Winter 2019.
Appreciation Letter for EECS 301 University of Michigan, Winter 2018.
Honorary Award from the Ministry of Science and Technology, Sharif University of Technology, Fall 2011-Winter 2012.
Silver Medal in the Iranian National Math Olympiad, Summer 2008.
Bronze Medal in the Iranian National Olympiad in Informatics, Summer 2007.
Co-organizer of Frontiers in Stochastic Control and Reinforcement Learning workshop, ACM SIGMETRICS, June 2026
Publication Co-Chair, ACM SIGMETRICS, 2025-2026
Co-organizer of Frontiers in Stochastic Control and Reinforcement Learning workshop, ACM SIGMETRICS, June 2025
Co-organizer of Reinforcement Learning and Multi-Agent Systems workshop, Performance, November 2023
Wolfram Mathematica Summer School, Boston, July 2023
MPS Workshop for Young Investigators, NSF, June 2022
Co-organizer of Learning-based Control of Queues and Networks workshop, ACM SIGMETRICS, June 2022
Visiting Researcher, Santa Fe Institute of Technology, Fall 2018