Arman Adibi

Arman Adibi

Assistant Professor, School of Computer and Cyber Sciences, Augusta University

Bio

I am an Assistant Professor in the School of Computer and Cyber Sciences at Augusta University. Previously, I was a postdoctoral researcher in Electrical and Computer Engineering at Princeton University, working with Prof. H. Vincent Poor and Prof. Sanjeev Kulkarni; I also collaborated with Prof. Vahid Tarokh (Duke) and Prof. Taposh Banerjee (University of Pittsburgh). I earned my Ph.D. in Electrical and Systems Engineering from the University of Pennsylvania under Prof. Hamed Hassani and worked closely with Prof. George J. Pappas, Prof. Aritra Mitra (NC State), and Prof. Aryan Mokhtari (UT Austin).

Research

I work on the theoretical foundations of AI, aiming to design scalable and reliable learning algorithms for nonstationary, distributed, and adversarial environments.

  • Generative AI & Diffusion Models. I study score-based diffusion, normalizing flows, and energy-based models, with theory for sample efficiency, stability, and control of memorization, as well as principled estimators via score matching.

  • Multimodal Machine Learning. I develop representation learning and fusion methods for heterogeneous data (vision, audio, text, and time series), with guarantees for alignment, robustness, and sequential decision-making across modalities.

  • Reinforcement Learning (federated & asynchronous). I analyze and design RL algorithms under delayed, partial, or adversarial updates, providing non-asymptotic guarantees for reliability in distributed systems.

  • Distributed Learning & Minimax Optimization. I build communication- and computation-efficient methods for convex and nonconvex minimax problems, including robustness to delays and Byzantine agents.

  • Change Detection under Uncertainty. I develop detectors for high-dimensional and unnormalized distributions (e.g., energy-based models) that adapt to nonstationarity with provable false-alarm and detection-delay guarantees.

  • Submodular Optimization & Meta-Learning. I create scalable algorithms for discrete decision-making and adaptive meta-learning, enabling near-optimal performance in large-scale, uncertain settings.

  • Adversarial Robustness & Decision-Making under Uncertainty. I study principled risk measures and worst-case analyses to ensure dependable behavior under distribution shift and adversarial perturbations.

Open Positions

I am currently recruiting highly motivated PhD students who have a strong mathematical background to join my research group. If you are interested in pursuing a PhD in a collaborative and dynamic environment, please send your CV and transcript to aadibi@augusta.edu with the subject line: “PhD Application – Augusta University.”