Research

My research interests include decision-making, reinforcement learning, and optimization, with a particular focus on robustness and uncertainty quantification and their applications to large language models and networked systems.

I am interested in the alignment and calibration of large language models through pre-training, supervised fine-tuning, and reinforcement learning. I am also interested in studying language models from the perspective of constraints, coordination, and interactions between their different components and agents.

Selected Publications

2026

• Nicolas Helson, Pegah Alizadeh, Anastasios Giovanidis: Selecting Offline Reinforcement Learning Algorithms for Stochastic Network Control. IEEE NOMS 2026. [arXiv]
• Théo Zangato, Aomar Osmani, Pegah Alizadeh: Meta-RL with Shared Representations Enables Fast Adaptation in Energy Systems. PAKDD 2026. [arXiv]

2024

• Athanasios Karapantelakis, Pegah Alizadeh, Abdulrahman Alabassi, Kaushik Dey, Alexandros Nikou: Generative AI in mobile networks: a survey. Annals of Telecommunications, 79(1-2): 15-33. [DOI]
• Théo Zangato, Aomar Osmani, Pegah Alizadeh: Enhancing Decision-Making in Energy Management Systems Through Action-Independent Dynamics Learning. ECAI 2024. [DOI]

2023

• Louis Zigrand, Roberto Wolfler Calvo, Emiliano Traversi, Pegah Alizadeh: Optimization-driven Demand Prediction Framework for Suburban Dynamic Demand-Responsive Transport Systems. IJCAI 2023. [DOI]

2022

• Aomar Osmani, Massinissa Hamidi, Pegah Alizadeh: Clustering Approach to Solve Hierarchical Classification Problem Complexity. AAAI 2022. [DOI]
• Pegah Alizadeh, Aomar Osmani, Sammy Taleb: Improving Imitation Learning by Merging Experts Trajectories. CIKM 2022. [DOI]
• Charly Alizadeh, Pegah Alizadeh, Miguel F. Anjos, Lucas Létocart, Emiliano Traversi: How to Learn the Optimal Clique Decompositions in Solving Semidefinite Relaxations for OPF. IJCNN 2022. [DOI]

2021

• Pegah Alizadeh, Emiliano Traversi, Aomar Osmani: Deterministic policies based on maximum regrets in MDPs with imprecise rewards. AI Communications, 34(4): 229-244. [DOI]
• Louis Zigrand, Pegah Alizadeh, Emiliano Traversi, Roberto Wolfler Calvo: Machine Learning Guided Optimization for Demand Responsive Transport Systems. ECML/PKDD 2021. [DOI]

Teaching

I have experience teaching courses on machine learning and artificial intelligence at the undergraduate and graduate levels. Below is the list of my ongoing courses.