Maryam Fazel

I am an Associate Professor in ECE, and hold adjunct appointments in the departments of Computer Science and Engineering, Mathematics, and Statistics at UW. My research interests are in convex optimization, algorithms, machine learning, and control. Prior to joining UW EE, I was a Research Scientist at Caltech. I received my PhD in Electrical Engineering from Stanford University where I was part of the Information Systems Lab, advised by Prof. Stephen Boyd.
I co-direct our new NSF TRIPODS Institute, ADSI.
I serve on the Editorial board of the MOS-SIAM Book Series on Optimization, and am an Associate Editor of the SIAM Journal of Optimization (SIOPT), and an associate editor of the new SIAM Journal on Mathematics of Data Science (SIMODS).
I am also the chair of the annual ECE Lytle Lecture Series committee, and a coorganizer of the interdepartmental CORE Seminar Series.

• My entry in the Mathematics Genealogy Project
• Google Scholar page
• A Microsoft Academic search page
• My Erdos number is 3!

News

·      Aug 2019: I am coorganizing the ADSI Workshop on <a href=”https://ajwagen.github.io/adsi_learning_and_control/”>Algorithmic Foundations of Learning and Control</a>. This event is cosponsored by our TRIPODS partner institute, IFDS at U Wisconsin.

·       Aug 2019: ADSI 2019 <a href=``https://alecgt.github.io/adsi_summer/”>ADSI Summer School on Foundations of Data Science <\a>. 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.
• Reza defended successfully and graduated in Aug 2017. Congratulations!!

Research Interests

Optimization theory and algorithms, their role in machine learning and data science. Online optimization and online resource allocation. Convex Optimization. Low-rank matrix modeling and rank minimization. Applications in ML, signal processing, and system identification.

Funding from the National Science Foundation (NSF), the Office of Naval Research (ONR), and the Defense Advanced Research Projects Agency (DARPA) is gratefully acknowledged.

Research group

Students:

• Omid Sadeghi Meibodi, EE (BS Sharif Univ of Technology, Iran)
• Yue Sun, EE (BS Tsinghua Univ, China)
• Romain Camilleri, CSE (ENS Paris-Saclay/Mines ParisTech, France). Co-advised with Zaid Harchaoui.
• Jingjing Bu, EE (BS Beihang Univeristy, China). Co-advised with Mehran Mesbahi.
• Mitas Ray, EE (BS UC Berkeley, CA). Co-advised with Lillian Ratliff.
• Andrew Wagenmaker, CSE (BS U Michigan, MI). Co-advised with Kevin Jamieson.

Alumni:

• Ting Kei Pong, PhD in Mathematics, June 2011. Co-advised with Prof. Paul Tseng.
  Currently: Assistant Professor, Dept. of Applied Mathematics, Hong Kong Polytechnic University.
• Brian Hutchinson, PhD in EE, August 2013. Co-advised with Prof. Mari Ostendorf.
  Currently: Assistant 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 Deepmind.
• Palma London, BS in EE and Math, June 2014. Currently: PhD student at Caltech.
• Karthik Mohan, PhD in EE, December 2014.
  Currently: Data Scientist at Amazon, Inc.
• James Saunderson, Postdoc (joint position with Caltech), Sep 2015-June 2016.
  Currently: Assistant Professor, Dept of Electrical and Computer Systems Engineering, Monash Univ, Australia.
• Amin Jalali, PhD in EE, August 2016.
  Currently: Discovery Institute Postdoc, University of Wisconsin.
• Dennis Meng, PhD in EE, May 2017.
• Reza Eghbali, PhD in EE, August 2017.
  Currently: Postdoc at the Simons Institute, Berkeley, CA.

Publications

Some Recent Talks:

• Simons Institute Open Lecture: Finding Low-Rank Matrices: From Matrix Completion to Recent Trends. November 2017. Part of the program Bridging Continuous and Discrete Optimization (where I was a semester-long visiting scholar).
• Simons Institute Workshop, September 2017. Talk on Online Optimization, Smoothing, and Competitive Ratio.
• Simons Institute Workshop, September 2014. Talk on Convex Relaxations for Recovering Simultaneously Structured Objects.

Published in Journal or Peer-reviewed Conference:

• R. Eghbali, J. Saunderson, M. Fazel, Competitive Online Algorithms for Resource Allocation over the Positive Semidefinite Cone, arxiv:1802.01312. Mathematical Programming Series B, Special issue on ISMP'18. 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, arxiv:1801.05039. 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. Matlab code.
• 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. Jalali, J. Saunderson, M. Fazel, B. Hassibi, Error bounds for Bregman Denoising and Structured Natural Parameter Estimation. Proc. International Symposium of Information Theory (ISIT), July 2017.
• R. Eghbali, M. Fazel, Decomposable Norm Minimization with Proximal-Gradient Homotopy Algorithm, arXiv:1501.06711. Computational Optimization and Applications, 66 (2), 345-381, March 2017.
• A. Jalali, Q. Han, I. Dumitriu, M. Fazel, Relative Density and Exact Recovery in Heterogeneous Stochastic Block Models. Proc. Neural Information Processing Systems (NIPS), Barcelona, Spain, Dec 2016.
  Full longer version on arxiv.
• R. Eghbali, M. Fazel, Designing smoothing functions for improved worst-case competitive ratio in online optimization. Proc. Neural Information Processing Systems (NIPS), Barcelona, Spain, Dec 2016.
  Full longer version on arxiv.
• R. Eghbali, M. Fazel, M. Mesbahi, Worst Case Competitive Analysis of Greedy Algorithm for Online Conic Optimization. Proc. Conference on Decision and Control (CDC), Las Vegas, NV, Dec 2016.
• D. Meng, R. Eghbali*, M. Fazel, M. Mesbahi, Online Algorithms for Network Formation. Proc. Conference on Decision and Control (CDC), Las Vegas, NV, Dec 2016.
• J. Saunderson, M. Fazel, B. Hassibi, Simple algorithms and guarantees for low rank matrix completion over F_2, to appear in Proc. 2016 IEEE International Symposium on Information Theory (ISIT), July 2016.
• K. Jaganathan, J. Saunderson, M. Fazel, Y. C. Eldar, B. Hassibi, Phaseless super-resolution using masks. Proc. 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), March 2016
• S. Oymak, A. Jalali, M. Fazel, Y. Eldar, B. Hassibi, Simultaneously Structured Models with Applications to Sparse and Low-rank Matrices. IEEE Trans. on Information Theory, 61(5): 2886-2908, May 2015.
• K. Dvijotham, E. Todorov, M. Fazel, Convex Structured Controller Design, IEEE Trans. on Control of Networked Systems, 2-1 (2015), pp. 1-10. arxiv link.
• B. Hutchinson, M. Ostendorf, M. Fazel, A Sparse Plus Low-Rank Exponential Language Model for Limited Resource Scenarios. IEEE Transactions on Audio, Speech, and Language Processing, 23(3), 494-504, March/April 2015.
• K.-M. Tan, P. London, K. Mohan, S.-I. Lee, M. Fazel, D. Witten, Learning Graphical Models With Hubs, Journal of Machine Learning Research (JMLR), 15(Oct):3297-3331, 2014. Related R code.
• K. Dvijotham, E. Todorov, M. Fazel, Universal Convexification via Risk-Aversion. Conference on Uncertainty in Artifical Intelligence (UAI), July 2014. Best Student Paper Award .
• K. Mohan, P. London, M. Fazel, D. Witten, S.-I. Lee, Node-Based Learning of Multiple Gaussian Graphical Models. Journal of Machine Learning Research (JMLR), 15(Feb):445-488, 2014. Related Matlab codes (.zip file).
• S. Oymak, A. Jalali, M. Fazel, B. Hassibi, Noisy estimation of simultaneously structured models: Limitations of convex relaxation. To appear in Proc. Conference on Decision and Control, Dec 2013. Longer version to be posted soon.
• K. Dvijotham, E. Theodorou, E. Todorov, M. Fazel, Convexity of Optimal Linear Controller Design. To appear in Proc. Conference on Decision and Control, Dec 2013.
• K. Dvijotham, E. Todorov, M. Fazel, Convex Control Design via Covariance Minimization. Proc. of Allerton Conference, Oct 2013.
• M. Fazel, T. K. Pong, D. Sun, P. Tseng, Hankel matrix rank minimization with applications in system identification and realization. SIAM Journal on Matrix Analysis and Applications, 34(3): 946-977, 2013. Related Matlab codes (zip file).
• B. Hutchinson, M. Ostendorf, M. Fazel, Exceptions in Language as Learned by the Multi-factor Sparse Plus Low-rank Language Model. Proc. Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), May 2013.
• F. Fazel, M. Fazel, M. Stojanovic. Random Access Compressed Sensing over Fading and Noisy Communication Channels. IEEE Trans. on Wireless Communications, 12(5): 2114-2125, May 2013.
• K. Mohan, M. Chung, S. Han, D. Witten, S.-I. Lee, M. Fazel, Structured Learning of Multiple Gaussian Graphical Models. Proc. Neural Information Processing Systems (NIPS), Dec 2012.
• K. Mohan, M. Fazel, Iterative Reweighted Algorithms for Matrix Rank Minimization. Journal of Machine Learning Research (JMLR), 2012. Related Matlab codes (zip file).
• B. Hutchinson, M. Ostendorf, M. Fazel, A Sparse Plus Low Rank Maximum Entropy Language Model. Proc. InterSpeech Conference, Sep 2012 (oral presentation).
• M. Nabi-Abdolyousefi, M. Fazel, Mehran Mesbahi, A Graph Realization Approach to Network Identification, Proc. of Conference in Decision and Control (CDC), Dec. 2012.
• F. Fazel, M. Fazel, M. Stojanovic, Compressed Sensing in Random Access Networks with Applications to Underwater Monitoring. Physical Communications Journal (Elsevier), special issue on Compressive Sensing in Communications.
• F. Fazel, M. Fazel, M. Stojanovic, Random Access Compressed Sensing: An Integrated Architecture For Energy-efficient Networking. Proc. Asilomar Conf. on Signals, Systems, and Computers, Nov 2011.
• B. Hutchinson, M. Ostendorf, M. Fazel, Low Rank Language Models for Small Training Sets. IEEE Signal Processing Letters. 18(9), pages 489-492, Sep 2011.
• F. Fazel, M. Fazel, M. Stojanovic, Random Access Compressed Sensing in Energy-Efficient Underwater Sensor Networks. Journal on Selected Areas in Communications (JSAC), 29(9), Sep 2011.
• S. Oymak, K. Mohan, M. Fazel, B. Hassibi, A Simplified Approach to Recovery Conditions for Low-rank Matrices. Proc. Intl. Sympo. Information Theory (ISIT), Aug 2011.
• R. Arora, A. Kapila , M. Gupta, M. Fazel, Clustering by Left-Stochastic Decomposition. Proc. of International Conference on Machine Learning (ICML), July 2011.
• F. Fazel, M. Fazel, M. Stojanovic, Design of a Random Access Network for Compressed Sensing. Proc. Information Theory and Applications Workshop (ITA), Feb 2011.
• F. Fazel, M. Fazel, M. Stojanovic, Random Access Compressed Sensing in Underwater Acoustic Networks. Proc. Allerton Conference on Communications, Control, and Computing, Sep 2010.
• K. Mohan, M. Fazel, Iterative Reweighted Least Squares for Matrix Rank Minimization, Proc. Allerton Conference on Communications, Control, and Computing, Sep 2010.
• B. Recht, M. Fazel, P. Parrilo, Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization. SIAM Review, Vol 52, no 3, pages 471-501, 2010. Arxiv link.
• K. Mohan, M. Fazel, New Restricted Isometry Results for Noisy Low-rank Matrix Recovery, Proc. Intl. Symp. Info. Thoery (ISIT), Austin, TX, June 2010.
• K. Mohan, M. Fazel, Reweighted Nuclear Norm Minimization with Application to System Identification, Proc. American Control Conference (ACC), 2010.
• D. Georgiev, M. Fazel, E. Klavins, Model Discrimination of Chemical Reaction Networks by Linearization, Proc. American Control Conference (ACC), 2010.
• K. Dvijotham, M. Fazel, A Nullspace Analysis of the Nuclear Norm Heuristic for Rank Minimization, Proc. of ICASSP 2010, Dallas, Texas, March 2010.
• M. Fazel, E. J. Candes, B. Recht, P. Parrilo, Compressed Sensing and Robust Recovery of Low Rank Matrices, Proc. of Asilomar Conference, Pacific Grove, CA, Nov 2008.
• N. Yamamoto, M. Fazel, Computational Approach to Quantum Encoder Design for Purity Optimization. Physical Review A, vol. 76, no. 1, July 2007. Available at http://link.aps.org/abstract/PRA/v76/e012327
• B. Recht, M. Fazel, P. Parrilo, Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization. Allerton Conference, Allerton House, Illinois, Sep 2007.
• M. Lobo, M. Fazel, and S. Boyd, Portfolio Optimization with Linear and Fixed Transaction Costs. Annals of Operations Research, special issue on Financial Optimization, 152(1):376-394, July 2007.
• D. Gayme, M. Fazel, J. Doyle, Complexity in Automation of SOS Proofs: An Illustrative Example. Proc. Conference on Decision and Control, San Diego, California, Dec 2006.
• M. Fazel, D. Gayme, M. Chiang, Transient Analysis for Wireless Power Control. Proc. Globecom Conference, San Francisco, California, Nov 2006.
• H. El-Samad, M. Fazel, X. Liu, A. Papachristodoulou, S. Prajna, Stochastic Reachability Analysis in Complex Biological Networks. Proc. American Control Conference, Minneapolis, Minnesota, June 2006.
• A. Fakheri, M. Fazel, A Methodology for Optimization of Shell and Tube Heat Exchangers in Series . International Journal of Heat Exchangers, volume VII, number 1, June 2006.
• M. Fazel, M. Chiang, Network Utility Maximization with Nonconcave Utilities Using Sum-of-Squares Method. Proc. Conference on Decision and Control, Seville, Spain, Dec 2005.
• T.-M. Yi, M. Fazel, X. Liu, T. Otitoju, A. Papachristodoulou, S. Prajna, and J. Doyle, Application of Robust Model Validation Using SOSTOOLS to the Study of G-Protein Signaling in Yeast . In Proc. Foundations of Systems Biology and Engineering, Santa Barbara, California, August 2005.
• M. Sharif, C. Florens, M. Fazel, B. Hassibi, Amplitude and Sign Adjustment for Peak to Average Power Reduction . IEEE trans. on Communications, volume 53, number 8, pp. 1243--1247, August 2005.
• M. Fazel, H. Hindi, and S. Boyd, Rank Minimization and Applications in System Theory. Proc. American Control Conference, Boston,
  Massachusetts, June 2004.
• M. Sharif, C. Florens, M. Fazel, B. Hassibi, Peak to Average Power Reduction Using Amplitude and Sign Adjustment. Proc. International Conference on Communications, Paris, France, June 2004.
• M. Fazel, H. Hindi, and S. Boyd, Log-det Heuristic for Matrix Rank Minimization with Applications to Hankel and Euclidean Distance Matrices. Proc. American Control Conference, Denver, Colorado, June 2003.
• M. Fazel, H. Hindi, and S. Boyd, A Rank Minimization Heuristic with Application to Minimum Order System Approximation. Proc. American Control Conference, Arlington, Virginia, June 2001.

<hr size=0 width="100%" align=center>

Teaching

2018-2019:

AA/EE/ME 510: Mathematical Foundations of Systems Theory
Fall 2018 Course page on Canvas

2017-2018:

AA/CSE/EE/ME 578: Convex Optimization
Winter 2018
Course page on Canvas

EE PMP 578: Convex Optimization
Spring 2018

2017: On sabbatical leave

2015-2016:

EE PMP 578: Convex Optimization (Optimization in System Sciences)
Fall 2015
Course Webpage

EE/AA/ME 578: Convex Optimization
Winter 2016
Course Webpage

EE 546 (special topics): Convex Optimization Algorithms
Spring 2016
Course webpage

2014-2015:

EE/AA/ME 578: Optimization in System Sciences
Winter 2015
Course Webpage

EE235: Continuous-time Linear Systems (Signals and Systems)
Spring 2015

2013-2014:

EE235: Continuous-time Linear Systems (Signals and Systems)
Fall 2013
Course webpage

EE/AA/ME 578: Optimization in System Sciences
Winter 2014

EE 546: Frontiers in Optimization: Convex Optimization Algorithms
Spring 2014
Course webpage

<hr size=0 width="100%" align=center>

Education

• Ph.D. Electrical Engineering, Stanford University, CA, March 2002
• M.S. Electrical Engineering, Stanford University, CA, June 1997
• B.Sc. Electrical Engineering, Sharif University of Technology, Tehran, Iran, 1995

Ph.D. Thesis

• Matrix Rank Minimization with Applications. Elec. Eng. Dept, Stanford University, March 2002.
  Thesis: (ps file), (pdf file), (gzipped ps file)

*** Page under construction! ***