Raoof Zare Moayedi

Education

Sharif University of Technology 2024 – present

M.Sc. in Computer Science · GPA: 19.71/20 · Ranked 1st in class (ongoing).

Master’s thesis: Minimax-Optimal Private Multi-Sampling from Gaussian Distributions.

Amirkabir University of Technology (Tehran Polytechnic) 2019 – 2023

B.Sc. in Mathematics · GPA: 18.99/20 · Ranked 2nd in graduating class.

Amirkabir University of Technology (Tehran Polytechnic) 2018 – 2023

B.Sc. in Computer Science · GPA: 18.82/20 · Ranked 3rd in graduating class.

Bachelor’s thesis: A Survey on Differentially Private Algorithms.

Research experience

EPFLAugust 2026 – present

Research Intern · E3 Program · Prof. Olga Fink

I’m working on graph neural networks that use the structure of conventional numerical solvers to predict fluid motion. The goal is to take larger time steps than the solvers can reliably take on their own, while keeping predictions accurate over long periods. Taking fewer steps would make these simulations less expensive.

University of CambridgeJune 2025 – March 2026

Remote Research Assistant · Dr. Amir Reza Asadi

Developed a geometry-adaptive algorithm for differentially private synthetic data. It uses the data’s intrinsic structure to improve accuracy and reduce computation, with stronger error guarantees than methods governed by the ambient dimension.

Geometry-Adaptive Mechanisms for Private Synthetic Data

Nanyang Technological UniversityJanuary – June 2025

Funded Visiting Research Student · Prof. Yew-Soon Ong

Worked on robust prompt tuning, superalignment, and task arithmetic, studying their connections to adversarial robustness. I examined when adapting a model to a new task or objective preserves its robustness, and when it makes the model easier to attack.

Imperial College LondonJune 2023 – June 2024

Remote Research Assistant · Dr. Seyed-Mohsen Moosavi-Dezfooli

Worked on transferring adversarial robustness from teacher models to smaller students through robust knowledge distillation. This work was published in IEEE TPAMI.

Allies Teach Better Than Enemies: Inverse Adversaries for Robust Knowledge Distillation

Also worked on two projects in adversarial robustness:

• Robust data pruning: studied how data preparation, example selection, and training on pruned data affect adversarial robustness.
• Input-space geometry: compared CNNs and Transformers, focusing on how architectural biases affect the connectivity and topology of regions in input space.

Publications & preprints

@article{Junhao_raoof,
  title = {{Allies Teach Better Than Enemies: Inverse Adversaries for Robust Knowledge Distillation}},
  author = {Dong, Junhao and Zare Moayedi, Raoof and Ong, Yew-Soon and Moosavi-Dezfooli, Seyed-Mohsen},
  year = {2026},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  doi = {10.1109/TPAMI.2026.3660863}
}

@article{raoofzareCU,
  title = {{CuPINN: Optimizing PINNs through Curvature Minimization and Residual Landscape Flattening}},
  author = {Zare Moayedi, Raoof and Abbaszadeh, Mostafa and Dehghan, Mehdi},
  year = {2025},
  journal = {Computer Methods in Applied Mechanics and Engineering},
  doi = {10.1016/j.cma.2025.118180}
}

@misc{raoof_synthetic,
  title = {{Geometry-Adaptive Mechanisms for Private Synthetic Data}},
  author = {Zare Moayedi, Raoof and Asadi, Amir R. and Yassaee, Mohammad Hossein and Aminian, Gholamali},
  year = {2026},
  eprint = {2609.33363},
  archivePrefix = {arXiv},
  note = {Preprint; Under review}
}

@unpublished{raoof_private_sampling,
  title = {{Minimax-Optimal Private Multi-Sampling from Gaussian Distributions}},
  author = {Zare Moayedi, Raoof and Yassaee, Mohammad Hossein and Ebrahimi, Javad B.},
  year = {2026},
  note = {Preprint}
}

@unpublished{raoof_private_splt,
  title = {{Fundamental Limits of Private Covariance Estimation under Vertical Partitioning}},
  author = {Zare Moayedi, Raoof and Halvachi, Paniz and Najafi, Amir and Yassaee, Mohammad Hossein},
  year = {2026},
  note = {Preprint}
}

@unpublished{raoof_spurious,
  title = {{Understanding When SGD Improves Robustness to Spurious Correlations}},
  author = {Mirzaie, Nahal and Zare Moayedi, Raoof and Jafarinia, Hossein and Rohban, Mohammad Hossein and Soleymani Baghshah, Mahdieh},
  year = {2026},
  note = {Under review}
}

@misc{parsa2023where2start,
  title = {{Where2Start: Leveraging Initial States for Robust and Sample-Efficient Reinforcement Learning}},
  author = {Parsa, Pouya and Zare Moayedi, Raoof and Bornosi, Mohammad and Bejani, Mohammad Mahdi},
  year = {2023},
  eprint = {2311.15089},
  archivePrefix = {arXiv},
  note = {Preprint}
}

* Equal contribution.

Honors & funding

• EPFL Excellence in Engineering (E3) Fellowship, 2026.
• Funded visiting research student position at NTU, 2025.
• Ranked 9th among 5,000 candidates in Iran’s National M.Sc. Computer Science Entrance Exam, 2024.

Teaching Assistant

Graduate courses: Learning Theory (Fall 2025), Information Theory (Fall 2024), Trustworthy Machine Learning (Fall 2024), Scientific Deep Learning (Fall 2024), Measure Theory and Probability (Fall 2022), Machine Learning (Fall 2022).

Undergraduate courses: Real Analysis (Spring 2023), Applied Linear Algebra (Fall 2022), Stochastic Process (Spring 2022), Computational Theory (Fall 2021).

Relevant coursework

Graduate courses (grades out of 20): Generative Models (20), Learning Theory (20), Advanced Statistics (20), Information Theory (20), Bandit Learning (20), Measure Theory and Probability (20), Advanced Algorithms (18.2), Functional Analysis (17).

Undergraduate courses (grades out of 20): Computer Graphics (20), Game Theory (20), Stochastic Process (20), Combinatorial Optimization (20).

Graduate-level audited courses: High-Dimensional Statistics, Convex Optimization, Discrete Differential Geometry, Introduction to Matroids, High-Dimensional Robust Statistics, Large Language Models.

Languages

Persian: Native · English: TOEFL iBT 101.