Shahriar Talebi

Science Center, Rm. 316.10

1 Oxford St

Cambridge, MA 02138

I am currently affiliated with the John A. Paulson School of Engineering and Applied Sciences (SEAS), the Faculty of Arts and Sciences (FAS), and the NSF AI Institute in Dynamic Systems (Dynamics AI).

I received my Ph.D. in control theory in 2023 under the supervision of Professor Mehran Mesbahi at the University of Washington, Seattle, where my research focused on constrained decision-making and control in complex systems. My dissertation, titled "Constrained Policy Synthesis: Riemannian Flows, Online Regulation, and Distributed Games," explored novel methods for policy optimization under constraints. Simultaneously, I earned my M.Sc. in Mathematics, specializing in differential geometry, under the supervison of Professor John M. Lee, also at the University of Washington. This unique combination of control theory and differential geometry has equipped me with a robust mathematical foundation for addressing challenges in scalable control and decision-making frameworks from a distinctive angle. Recently, I had the honor of being interviewed by Rodolphe Sepulchre in IEEE Control Systems Magazine.

My research focuses on developing rigorous mathematical frameworks that leverage geometry, machine learning, and control to study data-driven decision-making and data science. I address challenges in learning and decision-making in complex systems, with a focus on geometric methods for inference and decision-making under uncertainty. I have published over 20 papers and reviewed more than 40 papers (see my Web of Science profile summary). I am a recipient of the Excellence in Teaching Award at the University of Washington and have been recognized with several scholarships and fellowships throughout my academic career.

...more about me.

I received the B.Sc. degree in electrical engineering from the Sharif University of Technology, Tehran, Iran, in 2014, the M.Sc. degree in electrical engineering from the University of Central Florida (UCF), Orlando, FL, USA, in 2017, both in the area of control theory. I'm honored by the 2022 Excellence in Teaching Award at the University of Washington. I'm also a recipient of William E. Boeing Endowed Fellowship, Paul A. Carlstedt Endowment, and Latvian Arctic Pilot–A. Vagners Memorial Scholarship with UW in 2018 and 2019, and Frank Hubbard Engineering Scholarship with UCF in 2017.

News

Jun 8, 2024	📝 Check out our recent review on policy optimization in control focusing on its geometric properties and algoritmic implications Title: Policy Optimization in Control: Geometry and Algorithmic Implications (see the full paper)
May 14, 2024	📝 Our work on learning low-dim latent dynamics from high-dim observations is accepted in ICML 2024 (see you there) Title: Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds (see the full paper)
Feb 22, 2024	🗣 I’ll present in the ECE Department Seminars at the University of Hawaii Title: Unveiling Recent Advancements in Learning for Control and Filtering (see the flyer)
Jan 2, 2024	📝 Our work on data-driven policy iteration for distributed systems is accepted in IEEE TAC See the full paper
Dec 27, 2023	📝 I’m very much honored to be interviewed by Rodolphe Sepulchre in IEEE Control Systems Magazine (CMS) See the interview in IEEE CMS, issued Dec. 2023. It was an amazing opportunity to reflect back on my academic journey and a great chance to thank everyone supporting me in every step of the way!

Older News

Nov 1, 2023	📝 Our work on learning optimal filtering is accepted in NeurIPS 2023 (see you there) See the full paper and a short presentation (with the Chrome browser!)
Jun 1, 2023	👨🏻‍💻 I will be joining the Harvard University in Fall 2023 I’m very excited to work with Na (Lina) Li and Lucas Janson as a Postdoctoral Fellow in the Harvard John A. Paulson School of Engineering and Applied Sciences
May 23, 2023	🎓 I defended my Ph.D. dissertation Title: Constrained Policy Synthesis: Riemannian flows, Patterned linear Semigroup, and Online Regulation Committee members: Prof. Mehran Mesbahi (Chair), Prof. John M. Lee, Prof. James V. Burke, Prof. Maryam Fazel, Prof. Lillian J. Ratliff, and Prof. Amirhossein Taghvaei
May 21, 2023	📝 Our new work on learning optimal filtering is now available on arXiv: Title: Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances 🗣 I’ve presented its application to estimation for aeroelastic modal displacement of flexible wings at ACC 2023
Apr 21, 2023	📝 Our paper is accepted in IEEE Conference on Control Technology and Applications (CCTA) 2023: Title: Distributed Consensus on Manifolds using the Riemannian Center of Mass 🗣 We will present it on August 16-18, 2023 in Bridgetown, Barbados
Sep 7, 2022	📝 Our paper is accepted in IEEE Transactions on Automatic Control: see Policy Optimization over Submanifolds for Constrained Feedback Synthesis 🗣 I’ll present its application to structured and output-feedback problems at CDC 2022
Jul 7, 2022	🏆 I’ve been honored with the Excellence in Teaching Award @ UW This award recognizes sustained commitment to and distinguished achievement in classroom teaching
Mar 16, 2022	👨🏼‍🏫 I will be teaching Networked Dynamic Systems in Spring 2022 @ UW Check out the course website
Feb 10, 2022	🗣 Invited talk for RSRG group @ Caltech I'm presenting our work on distributed data-driven policy optimization Find the draft paper here or the conference version here
Jan 1, 2022	📝 See my latest publications on my google scholar

selected publications

Talebi, S., Alemzadeh, S., & Mesbahi, M. (2024). Data-Driven Structured Policy Iteration for Homogeneous Distributed Systems. IEEE Trans on Automatic Control (TAC), 69(9), 5979–5994.

@article{talebi2024data,
  title = {Data-Driven Structured Policy Iteration for Homogeneous Distributed Systems},
  author = {Talebi, Shahriar and Alemzadeh, Siavash and Mesbahi, Mehran},
  journal = {IEEE Trans on Automatic Control (TAC)},
  year = {2024},
  volume = {69},
  number = {9},
  pages = {5979-5994},
  publisher = {IEEE},
  link = {https://ieeexplore.ieee.org/abstract/document/10436325},
  selected = true
}

Talebi, S., Zheng, Y., Kraisler, S., Li, N., & Mesbahi, M. (2024). Policy Optimization in Control: Geometry and Algorithmic Implications. In Encyclopedia of Systems and Control Theor (to appear). arXiv preprint arXiv:2406.04243. Elsevier.

@inbook{talebi2024policy,
  title = {Policy Optimization in Control: Geometry and Algorithmic Implications},
  author = {{Talebi}, {Shahriar} and Zheng, Yang and Kraisler, Spencer and Li, Na and Mesbahi, Mehran},
  journal = {Encyclopedia of Systems and Control Theor (to appear). arXiv preprint arXiv:2406.04243},
  maintitle = {Encyclopedia of Systems and Control Theor (to appear)},
  publisher = {Elsevier},
  year = {2024},
  link = {https://arxiv.org/abs/2406.04243},
  selected = true
}

Talebi, S., Alemzadeh, S., Rahimi, N., & Mesbahi, M. (2022). On Regularizability and its Application to Online Control of Unstable LTI Systems. IEEE Trans on Automatic Control (TAC), 67(12), 6413–6428.

@article{talebi2021regularizability,
  title = {On Regularizability and its Application to Online Control of Unstable LTI Systems},
  author = {{Talebi}, {Shahriar} and Alemzadeh, Siavash and Rahimi, Niyousha and Mesbahi, Mehran},
  journal = {IEEE Trans on Automatic Control ({TAC})},
  year = {2022},
  volume = {67},
  number = {12},
  pages = {6413-6428},
  publisher = {IEEE},
  link = {https://ieeexplore.ieee.org/abstract/document/9627635/},
  selected = true
}

Talebi, S., & Mesbahi, M. (2024). Policy optimization over submanifolds for linearly constrained feedback synthesis. IEEE Transactions on Automatic Control, 69(5), 3024–3039.
```
@article{talebi2021policy,
  title = {Policy optimization over submanifolds for linearly constrained feedback synthesis},
  author = {Talebi, Shahriar and Mesbahi, Mehran},
  journal = {IEEE Transactions on Automatic Control},
  year = {2024},
  volume = {69},
  number = {5},
  pages = {3024-3039},
  publisher = {IEEE},
  link = {https://ieeexplore.ieee.org/abstract/document/10224332},
  selected = true
}
```

Talebi, S., Taghvaei, A., & Mesbahi, M. (2023). Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances. Advances in Neural Information Processing Systems (NeurIPS), 36, 69546–69585.

@inproceedings{talebi2023data,
  author = {Talebi, Shahriar and Taghvaei, Amirhossein and Mesbahi, Mehran},
  booktitle = {Advances in Neural Information Processing Systems ({NeurIPS})},
  pages = {69546--69585},
  publisher = {Curran Associates, Inc.},
  title = {Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances},
  volume = {36},
  year = {2023},
  link = {https://proceedings.neurips.cc/paper_files/paper/2023/file/dbe8185809cb7032ec7ec6e365e3ed3b-Paper-Conference.pdf},
  selected = true
}

Talebi, S., & Li, N. (2024). Uniform Ergodicity and Ergodic-Risk Constrained Policy Optimization. ArXiv Preprint ArXiv:2409.10767.
```
@article{talebi2024uniform,
  title = {Uniform Ergodicity and Ergodic-Risk Constrained Policy Optimization},
  author = {{Talebi}, {Shahriar} and Li, Na},
  journal = {arXiv preprint arXiv:2409.10767},
  year = {2024},
  link = {https://arxiv.org/pdf/2409.10767},
  selected = true
}
```

Zhang, Y., Talebi, S., & Li, N. (2024). Learning Low-dimensional Latent Dynamics from High- dimensional Observations: Non-asymptotics and Lower Bounds. Proc. of the 41st Int Conf on Machine Learning (ICML), 235, 59851–59896.

@inproceedings{zhang2024learning,
  title = {Learning Low-dimensional Latent Dynamics from High- dimensional Observations: Non-asymptotics and Lower Bounds},
  author = {Zhang, Yuyang and Talebi, Shahriar and Li, Na},
  booktitle = {Proc. of the 41st Int Conf on Machine Learning (ICML)},
  pages = {59851--59896},
  year = {2024},
  volume = {235},
  series = {Proceedings of Machine Learning Research},
  month = {21--27 Jul},
  publisher = {PMLR},
  link = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/zhang24bh/zhang24bh.pdf},
  selected = true
}