Maryam Fazel

Moorthy Family Professor
Data Science, Robotics and Controls
Room CSE230, Paul Allen Center
Campus Box 352500
University of Washington
Seattle, WA 98195
Email: mfazel@uw.edu

Bio: Maryam holds the Moorthy Family Inspiration Career Development Professorship in ECE, and adjunct appointments in the departments of Mathematics, Statistics, and the Allen School of Computer Science and Engineering at UW. Her current research interests are Optimization in Machine Learning and AI, Learning and Control, and Online and Reinforcement learning. Maryam is the director and lead PI of the Institute for Foundations of Data Science (IFDS), a multi-university research institute aiming to develop theoretical foundations for machine learning and data science, funded by a $12.5 million NSF TRIPODS Phase II grant, launched in September 2020. Previously, she co-directed the Algorithmic Foundations of Data Science Institute (ADSI), a TRIPODS Phase I institute that was a pre-cursor to IFDS. She is a recipient of the NSF CAREER Award (2009), UWEE Outstanding Teaching Award (2009), and UAI conference Best Student Paper Award (with her student K. Dvijotham, 2014), and coauthored a paper on low-rank matrix estimation selected by ScienceWatch as the “Fast Breaking Paper” (based on citation numbers) in the area of Mathematics (August 2011). Prior to joining UW, she was a postdoctoral scholar at Caltech; and received her PhD in EE from Stanford University where she was advised by Prof. Stephen Boyd. She received her BS in EE from Sharif University of Technology in Iran. Maryam was a Founding Associate Editor of the SIAM Journal on Mathematics of Data Science (SIMODS), and currently serves as an Action Editor of J. of Machine Learning Research (JMLR), and on the Editorial board of the MOS-SIAM Book Series on Optimization. She also serves on the Advisory board of the UW-Amazon Science Hub, and the executive committee of the eScience Institute. Maryam is a Program Chair of the ICML 2025 conference.

Short Bio: Maryam Fazel is the Moorthy Family Professor of Electrical and Computer Engineering at the University of Washington, with adjunct appointments in Computer Science and Engineering, Mathematics, and Statistics. Maryam received her MS and PhD from Stanford University, her BS from Sharif University of Technology in Iran, and was a postdoctoral scholar at Caltech before joining UW. She is a recipient of the NSF Career Award, UWEE Outstanding Teaching Award, a UAI conference Best Student Paper Award with her student. She directs the Institute for Foundations of Data Science (IFDS), a multi-site NSF TRIPODS Institute. She serves on the Editorial board of the MOS-SIAM Book Series on Optimization, and as an Acting Editor of the Journal of Machine Learning Research. Her current research interests are in the area of optimization in machine learning and control.

News

July 2024: Keynote talk at the SIAM Annual Meeting, Spokane, WA, July 2024.
May 2024: Avinandan Bose receives a a Fellowship from the Meta AI Mentorship Program. Congratulations Avi!
April 2024: Group alumnus professor Ting Kei Pong just became a Full Professor at the Applied Math Dept. at Hong Kong Polytechnic University. Congratulations Ting Kei!
March 2024: I will be a Program Chair of ICML 2025, in Vancouver, BC, July 13-19, 2025.
January 2024: Keynote talk at Conf. on Parsimony and Learning (CPAL), Hong Kong, Jan 3-6.
November 2023: Gave a talk at the Simons Institute Workshop on Optimization and Algorithm Design.
October 2023: Gave a talk at the Workshop on Foundations of Fairness, Privacy, and Causality in Graphs, organized by our IFDS partners at UC Santa Cruz.
October 2023: Gave a talk and was a panelist at the Workshop on New Frontiers in Networked Dynamical Systems, honoring the 75th birthday of Prof. John Baras.
October 2023: Spoke in the Distinguished Speaker Series at the Univ of Chicago.
October 2023: Group alumnus professor Brian Hutchinson just became a Full Professor at the CS Dept at Western Washington University. Congratulations Brian!
July 2023: Zhihan Xiong receives a 2nd year of Fellowship from the Meta AI Mentorship Program. Congratulations Zhihan!
June 2023: Please see our Tutorial Session: 1/2-day Tutorial on Learning for Dynamics and Control Conference (L4DC) 2023. Link.
June 2023: Please see our Workshop: "Intersections between Policy Optimization, Reinforcement Learning, and Feedback Control": 1-day Workshop at American Control Conference (ACC) 2023. Link.
May 2023: Our survey paper "Toward a Theoretical Foundation of Policy Optimization for Learning Control Policies" is out! (published in Annual Review of Control, Robotics, and Autonomous Systems, May 2023).
August 2023: IFDS Annual Meeting held at U Wisconsin-Madison, Aug 1-2, 2023.
October 2022: Talk abstracts and videos for the IFDS Summer Workshop on Distributional Robustness are now available through the event website.
September 2022: Zhihan Xiong receives a Fellowship from the Meta AI Mentorship Program. Congratulations Zhihan!
August 2022: Adhyyan Narang receives the UW-Amazon Hub PhD Fellowship. Congratulations Adhyyan!
August 2022: All material for the summer school PIMS-IFDS-NSF Summer School on Optimal Transport, June 19-July 1st, 2022, University of Washington are now available; please check the website.
June 2022: IFDS is organizing a summer research Workshop on Distributional Robustness in Data Science, Aug 4-6, 2022, University of Washington Campus.
March 2022: IFDS has partnered with the UW Taskar Center to co-organize AI4All@UW 2022, Aug 8-20, 2022, held virtually.
Feb 2022: IFDS is co-organizing the PIMS-IFDS-NSF Summer School on Optimal Transport, June 19-July 1st, 2022, University of Washington Campus.
Sep 2020: We won a NSF TRIPODS Phase II Award and launched the Institute for Foundations of Data Science (IFDS), with partners U Wisconsin, UC Santa Cruz, and U Chicago!
Aug 2020: I am honored to be named as the inaugural Moorthy Family Inspiration Career Development Professor.
Aug 2019: I am co-organizing the ADSI Workshop on Algorithmic Foundations of Learning and Control. This event is cosponsored by our TRIPODS partner institute, IFDS at U Wisconsin.
Aug 2019: I am co-organizing the 2019 ADSI Summer School on Foundations of Data Science. This event is cosponsored by our TRIPODS partner institute, IFDS at U Wisconsin.
Sep 2018: ADSI recieved three new NSF TRIPODS+X grants! NSF press release
I am the PI on "TRIPODS+X:EDU: Foundational Training Neuroscience and Geoscience via Hack Weeks," and a co-PI on "TRIPODS+X:RES: Safe Imitation Learning for Robotics" (with PI Zaid Harchaoui).
UW News press release
Aug 2018: ADSI co-organized the Workshop on Nonconvex Formulations and Algorithms in Data Science, with our TRIPODS partner institute IFDS at the University of Wisconsin, Madison.Videos of talks are available here.
July 2018: ADSI co-organized the Summer School on Fundamentals of Data Analysis, with our TRIPODS partner institute IFDS at the University of Wisconsin, Madison. Videos of lectures are available here.
Apr 2018: I am the PI on a new grant from the DARPA Lagrange program (an exciting recently-established program on optimization) on "Control and Learning of Uncertain Dynamical Systems," with co-PIs Sham Kakade and Mehran Mesbahi.
Jan 2018: ADSI launched a new blog highlighting research breakthroughs by its members and affiliates, check it out!
Sep 2017: We founded ADSI: Algorithmic Foundations of Data Science Institute, our NSF TRIPODS Institute. I am the co-director (with Sham Kakade). Other members of the core PI team are: Dmitriy Drusvyatskiy, Zaid Harchaoui, and Yin Tat Lee.
Aug 2017: We received an NSF TRIPODS Award! This funds the Phase I of an NSF Institute at UW aiming to build a Theoretical Foundation for Data Science by bridging Mathematics, Statistics, and Theoretical Computer Science.
NSF announcement, UW press here, and here.

Honors, Awards, Keynotes:

Plenary Speaker (one of three), American Control Conference, July 2025.
Semi-plenary Speaker, Intl. Conf. on Continuous Optimization, July 2025.
Keynote Speaker, SIAM Annual Meeting, July 8-12, 2024, Spokane, WA.
Keynote Speaker, Conf. on Parsimony and Learning (CPAL), Jan 2024, Hong Kong.
Keynote Speaker (one of three), Conf. on Learning Theory (COLT), July 2022, London, UK.
NSF TRIPODS Phase II (2020-2025). Director and lead principal investigator of IFDS (Inst. For Foundations of Data Science), a multi-site Institute with partners at Universities of Wisconsin, California at Santa Cruz, and Chicago.
Moorthy Family Professor in ECE, August 2020-present.
NSF TRIPODS (2017-2020): Co-director (with S. Kakade) of the Phase I NSF Institute: Algorithmic Foundations for Data Science Institute (ADSI). Co-PIs: Dmitriy Drusvyatskiy, Zaid Harchaoui, Yin Tat Lee. NSF announcement and press, also here.
Keynote Speaker, Intl. Symposium on Mathematical Programming (ISMP), July 2018, Bordeaux, France.
Simons Institute Open Lecture (one of three public lectures per semester, organized by the Simons Institute, UC Berkeley), November 2017, Berkeley, CA.
Plenary Speaker, SIAM Applied Linear Algebra Conference, October 26-30 2015, Atlanta, GA.
Plenary Speaker, SPARS Conference 2015 (Signal Processing with Adaptive Sparse Representations), July 2015, Cambridge, UK.
Best Student Paper Award, Uncertainty in Artificial Intelligence (UAI) 2014 (with K. Dvijotham and E. Todorov).
Plenary Speaker, 2013 International Linear Algebra Society Conference, June 3-7 2013, Providence, RI.
Coauthored paper selected by ScienceWatch as the “Fast Breaking Paper” in the area of Mathematics, August 2011.
NSF CAREER Award, National Science Foundation, 2009.
Outstanding Teaching Award, 2009, University of Washington Electrical Engineering Dept. (Annual department-level teaching award, nominated by students)
EE Dept. Award for ranking first among all freshmen, 1990, Electrical Engineering Dept., Sharif University of Technology, Tehran, Iran
Ranked first in the country in the Nationwide Entrance Examination to all Iranian Universities (among ~1 million applicants), 1990, Iran. Presidential Letter of Honor awarded by the Iranian President, 1990, Iran.

Some of our projects (also see recent publications):

Theory of Deep Learning (e.g., generalization properties of flat minima of training loss; theory for new deep architectures)
Theoretical Foundation for Policy Optimization for Designing Control Policies (Bridging control theory and RL)
Machine Learning Markets: Dynamics, Competition, and Interventions (NSF AF) (2023-2026). PIs: M. Fazel, J. Morgenstern, L. Ratliff, S. Dean (Cornell). (Multi-learner ML)
Toward a Mathematical Foundation of Deep Reinforcement Learning (NSF CIF) (2022-2026). PIs: S. Du, M. Fazel, T. Ma (Stanford), J. D. Lee (Princeton). (Reinforcement Learning theory)
Learning in Decision-dependent Games (Optimization, ML and game theory)
Learning and Optimal Experimental Design with a Budget (NSF CIF) (2020-2024). PIs: M. Fazel, K. Jamieson. (Active/Interactive Learning)
Institute for Foundations of Data Science (NSF TRIPODS Phase II Institute) (2020-2025)
Safe Imitation Learning for Robotics. NSF TRIPODS+X (2018-2022). PI: Z. Harchaoui; Co-PIs: M. Fazel, S. Kakade, S. Srinivasa
Algorithmic Foundations of Data Science Institute (NSF TRIPODS Phase I) (2017-2020)
Control and Learning of Dynamical Systems: Optimization, Sampling, and Regret (DARPA Lagrange, 2018-2019)
ADAPT: Analytical Framework for Actionable Defense against Advanced Persistent Threats (led by UW PI Radha Poovendran) (ONR MURI 2016-2021)

Selected papers below. Please see my Google Scholar page for a complete list.

M. Ray*, O. Sadeghi*, L. Ratliff, M. Fazel, Function Design for Improved Competitive Ratio in Online Resource Allocation with Procurement Costs, To appear in INFORMS J. on Optimization.
A. Narang, O. Sadeghi, L. J Ratliff, M. Fazel, J. Bilmes, Efficient Interactive Maximization of BP and Weakly Submodular Objectives, Proc. Uncertainty in AI Conf., 2024.
A. Bose, S. Du, M. Fazel, Offline Multi-task Transfer RL with Representational Penalization, preprint arXiv:2402.12570.
A. Bose, M. Curmei, D.L. Jiang, J. Morgenstern, S. Dean, L. J. Ratliff, M. Fazel, Initializing Services in Interactive ML Systems for Diverse Users, preprint arXiv:2312.11846.
Dean, M. Curmei, L. J. Ratliff, J. Morgenstern, M. Fazel, Emergent Segmentation from Participation Dynamics and Multi-learner Retraining, Proc. Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), May 2024.
Z. Xiong*, R. Camilleri, M. Fazel, L. Jain, K. Jamieson. A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity, Proc. Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), May 2024.
H. Jiang*, Q. Cui, Z. Xiong, M. Fazel, S. S. Du, A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning, Proc. Intl. Conf. on Learning Representations (ICLR), May 2024.
R. Raab, R. Boczar*, M. Fazel, Y. Liu, Fair Participation via Sequential Policies, Proc. AAAI Conf. on Artificial Intelligence, Feb 2024.
O. Sadeghi, M. Fazel, No-Regret Online Prediction with Strategic Experts, Proc. of Neural Information Processing Systems (NeurIPS), Dec 2023.
Z. Ren, Y. Zheng, M. Fazel, N. Li, On Controller Reduction in Linear Gaussian Control with Performance Bounds, Learning for Dynamics and Control Conf. (L4DC), Dec 2023.
O. Sadeghi, M. Fazel, Fast First-Order Methods for Monotone Strongly DR-Submodular Maximization, SIAM Conf. on Applied and Computational Discrete Algorithms (ACDA), June 2023.
Y. Qin, Y. Li , F. Pasqualetti, M. Fazel, S. Oymak, Stochastic Contextual Bandits with Long Horizon Rewards, Proc. of AAAI Conf. on Artificial Intelligence, Feb 2023.
H. Jiang, Q. Cui, Z. Xiong, M. Fazel, S. S. Du, Offline congestion games: How feedback type affects data coverage requirement, arXiv preprint arXiv:2210.13396.
B. Hu, K. Zhang, N. Li, M. Mesbahi, M. Fazel, T. Başar, Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies, arXiv preprint arXiv:2210.04810.
S. Dean, M. Curmei, L.J. Ratliff, J. Morgenstern, M. Fazel, Multi-learner risk reduction under endogenous participation dynamics, arXiv preprint arXiv:2206.02667.
Y. Sun, S. Oymak, M. Fazel, Finite Sample Identification of Low-order LTI Systems via Nuclear Norm Regularization, IEEE Open Journal of Control Systems, 2022.
Q. Cui*, Z. Xiong*, M. Fazel, S. S. Du, Learning in Congestion Games with Bandit Feedback, Proc. of Neural Information Processing Systems (NeurIPS), Dec 2022.
Z. Xiong, R. Shen, Q. Cui, M. Fazel, S. S. Du, Near-Optimal Randomized Exploration for Tabular Markov Decision Processes, Proc. of Neural Information Processing Systems(NeurIPS), Dec 2022.
Z. Ren, Y. Zheng, M. Fazel, L. Na, Escaping High-order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG) Control, Proc. of IEEE Conf. on Decision and Control (CDC), Dec 2022.
L. Ding, D. Drusvyatskiy, M. Fazel, Flat minima generalize for low-rank matrix recovery, arXiv preprint arXiv:2203.03756. To appear in the IMA J. on Information and Inference.
A. Narang, E. Faulkner, D. Drusvyatskiy, M. Fazel, L.J. Ratliff, Multiplayer Performative Prediction: Learning in Decision-Dependent Games, arXiv preprint arXiv:2201.03398. J. of Machine Learning Research (JMLR) 24, 2023.
A. Narang, E. Faulkner, D. Drusvyatskiy, M. Fazel, L.J. Ratliff, Learning in Stochastic Monotone Games with Decision-Dependent Data, AI and Statistics Conference (AISTATS), March 2022.
M. Ray, L.J. Ratliff, D. Drusvyatskiy, M. Fazel, Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environments, AAAI Confenece on Artificial Intelligence, Feb. 2022.
M. Fazel, Y.T. Lee, S. Padmanabhan, A. Sidford, Computing Lewis Weights to High Precision, Proc. Symp. on Discrete Algorithms (SODA), Jan 2022.
Y. Sun, M. Fazel, Learning Optimal Controllers by Policy Gradient: Global Optimality via Convex Parameterization, Proc. of IEEE Conf. on Decision and Control (CDC), Dec 2021.
Y. Sun, A. Narang, H.I. Gulluk, S. Oymak, M. Fazel, Towards Sample-Efficient Overparameterized Meta-Learning, Proc. Neural Information Processing Systems(NeurIPS), Dec 2021.
R. Camilleri, Z. Xiong, M. Fazel, L. Jain, K. Jamieson, Selective Sampling for Online Best Arm Identification, Proc. Neural Information Processing Systems (NeurIPS), Dec. 2021.
O.Sadeghi, M. Fazel, Differentially Private Monotone Submodular Maximization Under Matroid and Knapsack Constraints, Proc. AI and Statistics Conference (AISTATS), Apr 2021.
J. Diakonikolas, M. Fazel, L. Orecchia, Fair Packing and Covering on a Relative Scale, J. on Optimization, 2020. J. on Optimization, 2020.SIAM J. on Optimization, 2020.
O. Sadeghi, P. Raut, M. Fazel, A Single Recipe for Online Submodular Maximization with Adversarial or Stochastic Constraints, Proc. Neural Information Processing Systems (NeurIPS), Dec 2020.
Y. Sun, M. Fazel, Escaping from Saddle Points on Riemannian Manifolds, arxiv:1906.07355. Neural Information Processing Systems (NeurIPS) 2019, Vancouver, BC, Canada.
R. Eghbali, J. Saunderson, M. Fazel, Competitive Online Algorithms for Resource Allocation over the Positive Semidefinite Cone, Mathematical Programming Series B, Vol. 170, Issue 1, pp 267-292, July 2018.
M. Fazel, R. Ge, S. Kakade, M. Mesbahi, Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator, Proceedings of Intl. conference on Machine Learning (ICML), Stockholm, Sweden, July 2018.
D. Drusvyatskiy, M. Fazel, S. Roy, An optimal first order method based on optimal quadratic averaging, arXiv:1604.06543. SIAM J. on Optimization, 28-1 (2018), 251271.
A. Jalali, M. Fazel, L. Xiao, Variational Gram Functions: Convex Analysis and Optimization, arXiv:1507.04734. SIAM J. on Optimization, 27-4 (2017), pp. 2634-2661.
A. Jalalli, Q. Han, J. Dumitriu, M. Fazel, Exploiting Tradeoffs for Exact Recovery in Heterogeneous Stochastic Block Models, Proc. NIPS 2016 [Arxiv version]

I am fortunate to currently advise or co-advise these fantastic students:

Zhihan Xiong (CSE)
Adhyyan Narang (ECE) (co-advised with Lillian Ratliff)
Avinandan Bose (CSE) (co-advised with Lillian Ratliff)
Weihang Xu (CSE) (co-advised with Simon Du)

As well as IFDS postdocs:

Libin Zhu, IFDS Postdoc (co-mentored with Dima Drusvyatskiy)
Mo Zhou, Incoming IFDS Postdoc (co-mentored with Simon Du)
Natalie Frank, Incoming IFDS Postdoc (co-mentored with Bamdad Hosseini)

Alumni:

Ting Kei Pong, PhD in Mathematics, June 2011. Co-advised with Prof. Paul Tseng. Currently: Professor, Dept. of Applied Mathematics, Hong Kong Polytechnic University.
Brian Hutchinson, PhD in EE, August 2013. Co-advised with Prof. Mari Ostendorf. Currently: Professor, Department of Computer Science, Western Washington University.
Dvijotham Krishnamurthy, PhD in Computer Science and Engineering, June 2014. Co-advised with Prof. Emo Todorov. Currently: Research Scientist at Google.
Palma London, BS in EE and Math, June 2014. Currently: Postdoc at UC San Diego.
Karthik Mohan, PhD in EE, December 2014. Ex-data Scientist at Amazon and Meta. Currently: ML educator, UW affiliate faculty.
James Saunderson, Postdoc (joint position with Caltech), Sep 2015-June 2016. Currently: Associate Professor, Dept of Electrical and Computer Systems Engineering, Monash Univ, Australia.
Amin Jalali, PhD in EE, August 2016. Postdoc at Univ. of Wisconsin; Researcher at Technicolor Research. Currently: Independent researcher.
Dennis Meng, PhD in EE, May 2017. Currently: Apple, Inc.
Reza Eghbali, PhD in EE, August 2017. Currently: Data Science Health Innovation Fellow at University of California, San Francisco & University of California, Berkeley.
Tyler Johnson, PhD in EE, October 2018. Co-advised with Prof. Carlos Guestrin. Currently: Machine Learning Research Engineer, Apple Inc.
Jingjing Bu, PhD in EE, 2020. Co-advised with Prof. Mehran Mesbahi. Currently: Software engineer at TikTok Inc.
Mitas Ray, MS in EE, 2021. Co-advised with Prof. Lillian Ratliff. Currently: ML Software engineer at FICC.ai
Yue Sun, PhD in ECE, March 2022. Currently: Data Scientist at Microsoft (Bing Ads team).
Lijun Ding, IFDS Postdoc (co-mentored with Prof. Dima Drusvyatskiy). Currently: Assistant Professor in Mathematics, UC San Diego.
Omid Sadeghi, PhD in ECE, December 2023. Currently: Postdoc at MIT (OR Center).

Biography

Awards and Honors

Research Projects

Recent Publications

Students

In the Press

Be boundless