thesis.pdf

Mohammadreza Soltani

me

About me

I am currently a Ph.D. candidate in Electrical and Computer engineering department (ECpE) at Iowa State University (ISU). I am working as a research assistant under the supervision of Dr. Chinmay Hegde. I earned my first master degree in Electronics from Amirkabir Univesity of Technology, Tehran, Iran and my second master degree in Telecommunication with minor in math from University of Nebraska-Lincoln (UNL), Ne, USA in 2011 and 2014, respectively.

Research

My research interests broadly include Signal Processing, Machine Learning, Optimization, and Wireless Communication Networks. Specifically, I am interested in understanding the fundamental limits of different problems in signal processing and data science.

My google scholar     My CV

Thesis

Ph.D. thesis, ECpE Department, ISU, Feb 2019.
M.Soltani, Provable algorithms for nonlinear models in machine learning and signal processing.

Publications

  1. M.soltani, S. Jain, and A. Sambasivan, Learning Generative Models of Structured Signals from Their Superposition Using GANs with Application to Denoising and Demixing, 2019. (pdf)

  2. M. Soltani and C. Hegde, Fast Low-Rank Estimation for Ill-Conditioned Matrices, International Symposium on Information Theory (ISIT), June 2018. (pdf)

  3. M. Soltani and C.Hegde, Fast and Provable Algorithms for Learning Two-Layer Polynomial Neural Networks. (pdf)

  4. M. Soltani and C. Hegde, Towards Provable Learning of Polynomial Neural Networks Using Low-Rank Matrix Estimation, Artificial Intelligence and Statistics (AISTAT), April 2018. (Oral Presentation) (pdf)

  5. M. Soltani and C. Hegde, Fast Low-Rank Matrix Estimation without the Condition Number, Dec 2017. (pdf)

  6. M. Soltani and C. Hegde, Towards Provable Learning of Polynomial Neural Networks Using Low-Rank Matrix Estimation, NIPS Workshop On Deep Learning: Bridging Theory and Practice (DLP), Dec 2017 (pdf)

  7. M. Soltani and C. Hegde, Demixing Structured Superposition Signals from Periodic and Aperiodic Nonlinear Observations, IEEE GlobalSIP Symposium on Sparse Signal Processing and Deep Learning, Nov 2017. (pdf)

  8. V. Shah, M. Soltani, and C. Hegde, Reconstruction from Periodic Nonlinearities, with Applications to HDR Imaging, Asilomar Conference on Signals, Systems, and Computers, Nov 2017. (pdf)

  9. M.Soltani and C. Hegde, Improved Algorithms for Matrix Recovery from Rank-One Projections, poster presentation in Midwest Machine Learning Symposium (MMLS), May 2017. (Winner of the best poster award)

  10. M. Soltani and C. Hegde, Fast Algorithms for Learning Latent Variables in Graphical Models, ACM KDD Mining and Learning With Graphs (KDD MLG), Aug 2017. (pdf)

  11. M. Soltani and C. Hegde, Fast Algorithms for Demixing Sparse Signals from Nonlinear Observations, IEEE Transactions on Signal Processing, vol. 65, no. 16, p4209-4222, Aug 2017. (DOI)>

  12. M. Soltani and C. Hegde, Stable Recovery from Random Sinusoidal Feature Maps, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017. (pdf)

  13. M. Soltani and C. Hegde, Iterative Thresholding for Demixing Structured Superpositions in High Dimensions, NIPS Workshop on Learning in High Dimensions with Structure (LHDS), December 2016.(Oral presentation; acceptance rate: 2/50) (pdf)

  14. M. Soltani and C. Hegde, A Fast iterative Algorithm for Demixing Sparse Signals from Nonlinear Observations, IEEE GlobalSIP Symposium on Compressed Sensing and Deep Learning, Dec 2016. (pdf)

  15. M. Soltani and C. Hegde, Demixing sparse signals from nonlinear observations. Asilomar Conference on Signals, Systems, and Computers,, Nov. 2016. (pdf)

  16. M. Soltani, M. Hempel, and H. Sharif, Utilization of convex optimization for data fusion-driven sensor management in WSNs, International Wireless Communications and Mobile Computing Conference (IWCMC), 2015.

  17. M. Soltani, M. Hempel, and H. Sharif, Data fusion utilization for optimizing large-scale wireless sensor networks IEEE International Conference on Communications (ICC), 2014. (pdf)

  18. M. Maadani, A. Motamedi, and M. Soltani, EDCA Delay Analysis of Spatial Multiplexing in IEEE802. 11-Based Wireless Sensor and Actuator Networks, International Journal of Information and Electronics Engineering, Vol. 2, No. 3, May 2012. (pdf)

  19. M. Soltani, A novel Tunable Opportunistic Routing Protocol for WSN Applications. Amirkabir University of Technology, Technical Report, 2012. (pdf)

  20. M. Maadani, S. A. Motamedi, and M. Soltani, “Delay Analysis of MIMO-Enabled IEEE 802.11-Based Soft-Real-Time Wireless Sensor and Actuator Networks”, Dela, vol. 150, p200, 2011.

  21. M. Soltani, A. Motamedi, S. Ahmadi, and M. Maadani, Power-Aware and Void-Avoidant Routing Protocol for Reliable Industrial Wireless Sensor Networks, International Conference on Wireless Communications, Networking and Mobile Computing (WiCOM), 2011. (pdf)

Talk and poster presentation

  1. M. Soltani and C. Hegde Improved Algorithms for Matrix Recovery from Rank-One Projections, Midwest Machine Learning Symposium, Chicago, May 2017. "Winner of the Best Poster Award"

  2. M. Soltani and C. Hegde, Nonlinear demixing problem, Park City Mathematics Institute (PCMI), July 2016.

  3. M. Soltani, M. Hempel, H. Sharif, Data Fusion Utilization for Large-Scale Dynamic WSN Management, Poster presentation in UNL Research Fair, May 2014.

Teaching experience

  • T.A. at ISU, Fall 2017.
  • T.A. at ISU, 2015.
  • T.A. at UNL, Fall 2014.
  • Private tutor, Iran 2013.

    • Contact Information

    Electrical and Computer Engineering Department (ECpE)
    3201 Coover Hall, Iowa State University
    Ames, IA 50010, USA

    Email: msoltani@iastate.edu