I'm currently a Ph.D. student in the Electrical Engineering department at Stanford, advised by Emmanuel Candes.
. Starting September I will spend one year at UC Berkeley EECS/Stats as a postdoctoral researcher. My sponsers Berkeley are Ben Recht.
and Martin Wainwright.
. In August 2015 I will join the USC EE department as an assitant professor. I'm interested in various problems that lie at the interplay between statistics, convex optimization, geometric functional analysis and theoretical computer science. I'm interested in using these tools for the design and analysis of algorithms for data mining, machine learning, computer vision and signal/image processing. Recently, I've also become interested in the analysis of non-convex problems via iterative methods and the interactions between convex optimization and algebraic geometry.
Email: mahdisol@stanford.edu
Office: 380-U, Mathematics, Building 380, 450 Serra Mall, Stanford, CA 94305
. Starting September I will spend one year at UC Berkeley EECS/Stats as a postdoctoral researcher. My sponsers Berkeley are Ben Recht.
and Martin Wainwright.
. In August 2015 I will join the USC EE department as an assitant professor. I'm interested in various problems that lie at the interplay between statistics, convex optimization, geometric functional analysis and theoretical computer science. I'm interested in using these tools for the design and analysis of algorithms for data mining, machine learning, computer vision and signal/image processing. Recently, I've also become interested in the analysis of non-convex problems via iterative methods and the interactions between convex optimization and algebraic geometry.
Email: mahdisol@stanford.edu
Office: 380-U, Mathematics, Building 380, 450 Serra Mall, Stanford, CA 94305
-
All publications unless specified are based on alphabetic ordering of the names.
- Phase retrieval via Wirtinger Flow: Theory and Algorithms. (website)
E. J. Candes, X. Li, and M. Soltanolkotabi. - Robust Subspace Clustering. (website)
M. Soltanolkotabi, E. Elhamifar, and E. J. Candes. To appear in Annals of Statistics. - A Geometric Analysis of Subspace Clustering with Outliers. (code)
M. Soltanolkotabi and E. J. Candes. Annals of Statistics 40(4), 2195--2238, 2012. - Discussion of "Latent Variable Graphical Model Selection via Convex Optimization".
E. J. Candes and M. Soltanolkotabi. Annals of Statistics 40(2), 1997--2004, 2012. - A Unified Approach to Sparse Signal Processing.(during undergrad)
F. Marvasti, A. Amini, F. Haddadi, M. Soltanolkotabi, B. Khalaj, A. Aldroubi, S. Sanei and J. Chambers. EURASIP Journal on Advances in Signal Processing. - phase retrieval in near linear time.(will be available soon)
E. J. Candes, X. Li, and M. Soltanolkotabi. - Compressive sensing and sparse recovery with coherent and redundant dictionaries.(will be available soon)
E. J. Candes and M. Soltanolkotabi. - From robust subspace clustering to full-rank matrix completion.(Extended abstract-complete version will be available soon as part of a review article)
E. J. Candes, L. Mackey, and M. Soltanolkotabi. - Errorless Codes for Over-loaded Wireless CDMA with Active User Detection.
P. Pad, M. Soltanolkotabi, S. Hadikhanlou, A. Enayati and F. Marvasti. Proc. of the International Conference on Communications, ICC 2009, Dresden, Germany. - OFDM Channel Estimation based on Adaptive Thresholding for Sparse Signal Detection.
M. Soltanolkotabi, A. Amini and F. Marvasti. Proc. of European Signal Processing Conference, EUSIPCO 2009. - Throughput Capacity of a Multi-channel Multi- hop Mobile Ad-hoc Network.
M. Soltanolkotabi and F. Ashtiani. Proc. of International Conference on Telecommunications, ICT 2009. - A Practical Sparse Channel Estimation for Current OFDM Standards.
M. Soltanolkotabi, M. Soltanalian, A. Amini and F. Marvasti. Proc. of International Conference on Telecommunications, ICT 2009. - Salt and Pepper Noise Removal for Images.
S. Feizi-Khankandi, S. Zahed Pour, M. Soltanolkotabi, A. Amini and F. Marvasti. Proc. of International Conference on Telecommunications, ICT 2008.
Publications
Journals
In progress
Conferences (during undergrad)
- Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
- CMStatistics, Pisa, Italy, December 2018.
- Canadian Mathematical Society winter meeting, Vancouver, Canada, December 2018.
- From shallow to deep: learning neural networks via gradient descent.
- Department of Electrical Engineering, University of Pennsylvania, Philadelphia, PA, October 2018.
- Annual Allerton Conference on Communication, Control, and Computing, Allerton, IL.
- International Symposium on Mathematical Programming (ISMP), Bordeaux, France, July 2018.
- Nonconvex optimization meets suprema of stochastic process: From phase retrieval to deep learning.
- IPAM culminating workshop on Quantitative Linear Algebra, Lakearrowhead, CA, June 2018.
- From shallow to deep: Learning neural networks via gradient descent.
- Simons Foundations of Machine Learning Reunion Workshop, Berkeley, CA, June 2018.
- Nonconvex optimization for high-dimensional learning: ReLUs, neural nets and beyond
- Workshop on Applied Harmonic Analysis and Data Processing, Oberwolfach Research Institute for Mathematics, German Black Forest, March 2018.
- Courant Institute of Mathematical Sciences, Math and Data Seminar, New York, NY, March 2018.
- Program in Applied and Computational Mathematics (PACM) colloquim, Princeton, NJ, March 2018.
- Learning from signals and data via nonconvex optimization: ReLUs, neural nets and beyond
- ARO Workshop on data science, a uni ed vision towards structured and unstructured data analysis, Raleigh, NC, November 2017
- Directions and open problems in elements of non-convex optimization
- Workshop on Beyond Convexity: Emerging Challenges in Data Science, Ban International Research Station, Oaxaca, Mexico, October 2017
- Nonconvex optimization meets supremum of stochastic processes
- Probability Seminar, UC Irvine, CA, October 2017
- Discrete submodular optimization via continuous nonconvex optimization
- Asilomar invited session, Asilomar, CA, October 2017
- Nonconvex Optimization for High-Dimensional Learning: From neural networks to submodular maximization
- Workshop on Fast Iterative Methods in Optimization, Simons Institute, Berkeley, CA, October 2017
- Leveraging prior knowledge in phase retrieval via Wirtinger Flows: from theory to practice
- Workshop on Phaseless Imaging in Theory and Practice: Realistic Models, Fast Algoithms, and Recovery Guarantees, Institute for Mathematics and its Applications, Minneapolis, MN, August 2017 - Nonconvex Optimization for High-Dimensional Learning: From Phase Retrieval to Submodular Maximization
- EE Systems Seminar, California Institute of Technology, Pasadena, CA, May 2017
- EE Systems Seminar, North Carolina State, Durham, CA, June 2017 - Breaking sample complexity barriers via nonconvex optimization.
- SIAM conference on Optimization, Vancouver, Canada, May 2017.
- Joint Mathematical Meeting, Special Session on Mathematics of Signal processing, Atlanta, GA, January 2017.
- International Conference on Continuous Optimization (ICCOPT), Tokyo, August 2016. - Generic Chaining meets nonconvex optimization.
- NII Shonan Meeting on ``Recent Advances in Randomized Numerical Linear Algebra", NII Shonan Meeting, Tokyo, July 2016.
- Workshop on Chaining Methods and their Applications to Computer Science, Harvard University, June 2016. - Finding Low-complexity models without the shackles of convexity.
- Workshop on Low complexity models in signal processing, Hausdorff research institute for mathematics (HIM), Bonn, Germany, Feb. 2016. - Structured signal recovery without the shackles of convexity.
- Claremont Mckenna College, Math department September, 2016.
- Statistics Seminar, University of California, Los Angeles(UCLA), May 2016.
- International Matheon Conference on Compressed Sensing and its Applications, Berlin, Dec 2015.
- SIAM Conference on Applied Linear Algebra, Atlanta, October 2015.
- Sharp time-data tradeoffs for linear inverse problems
- International Symposium on Optimization, Pittsburg, July 2015. - Robust Subspace Clustering.
- Stanford Biostatistics Seminar, February 2014.
- ICML Spectral Learning Workshop, June 2013.
- Asilomar Conference on Signals, Systems, and Computers.
- MURI annual meeting, Princeton, October 2012.
- Information Theory and Applications workshop, Feb. 2013. - A Geometric Analysis of Subspace Clustering with Outliers.
- Berkeley Robotics Lab, Febuary 2012.
- High-Dimensional Phenomena in Statistics and Machine Learning Seminar, Georgia Tech., July 2012.
- Workshop on Modern Massive Data Sets (MMDS), Stanford, July 2012.
Invited Talks/Slides
Instructor:
EE 364a: Convex Optimization, Summer 2011.TA:
Stanford CS:- CS 229: Machine Learning, Fall 2012.
Stanford EE:
- EE 278: Statistical Signal Processing, Summer 2010.
Stanford Math:
- Math 104: Linear Algebra, Winter 2012.
Stanford Statistics: