Table of Contents

Alireza Sadeghi

Hello and welcome to my Webpage!

Alireza Sadeghi's Photo

Contact:

[Email] | [Google Scholar]

About Me

I am a Postdoctoral associate at the Electrical & Computer engineering department at the University of Minnesota, Twin Cities, and a member of the Signal Processing in Networking and Communications (SPiNCOM) group under the supervision of Professor Georgios B. Giannakis. I obtained my B.Sc. degree (with Honors) from the Iran University of Science and Technology in 2012, and M.Sc. degree from the University of Tehran in 2015, both in Electrical & Computer Engineering. In 2015 and before starting his PhD I spent 6 month as a visiting scholar at the University of Padova, Padova, Italy working at the SIGnal processing and NETworking (SIGNET) research group under supervision of Professor Michele Zorzi. I obatined my PhD in Electrical & Computer Engineering with a Minor in Computer Science from the University of Minnesota in 2021. Before starting this role at the University of Minnesota as research associate, I played a pivotal role as a full-time Data Scientist at 3M Corporation, where I was working on Natural Language Generation, Processing, and Inference using state-of-the-art NLP deep generative models such as BART, GPT-2, and BERT, among others. During the summer of 2021 I was an intern at Microsoft Research focusing on Data Science and Optimization to seamlessly integrate renewable energy into the operation of data centers.

Research interests

My research involves Signal Processing, Statistical Learning, Machine Learning, and Optimization with their applications in designing reliable, scalable, and efficient cyber-physical systems including next-generation wireless and power networks. Particularly I am interested in designing robust and scalable supervised, reinforcement, semi-supervised, and federated learning algorithms. Specifically, I am currently working on Robust Meta-Learning, Self-supervised Learning, and Representation Learning with Weak supervision.

Education

University of of Minnesota Twin Cities, Minneapolis, MN, USA 2016 - 2021

Ph.D. in Electrical and Computer Engineering, Major: Signal Processing and Machine Learning

Minor in Computer Science

University of Tehran, Tehran, Iran 2012 - 2015

M.Sc. in Electrical and Computer Engineering, Major: Communication Systems

Iran University of Science and Technology, Tehran, Iran 2008 - 2012

B.Sc. (with Honors) in Electrical and Computer Engineering, Major: Communication Systems

Publications

Book Chapters

  1. A. Sadeghi, G. B. Giannakis, G. Wang, and Fatemeh Sheikholeslami, Reinforcement Learning for Caching with Space-Time Popularity Dynamics. Edge Caching for Mobile Networks, by V. Poor and W. Chen Editors, Insti- tution of Engineering and Technology (IET)-Telecommunications, 2021.
  2. J. Chen, H. Cao, A. Sadeghi, and G. Wang, Learning Shared and Discriminative Information from Multi-view Data. Recent Advancements in Multi-View Data Analytics, pp. 239-268, Springer, 2022.

Journals

  1. A. Sadeghi, G. Wang, and G. B. Giannakis,“Learning Robust to Distributional Uncertainties and Adversarial Data,” IEEE J. Sel. Areas Info. Theory, Special Issue: Information-Theoretic Methods for Trustworthy and Reliable Machine Learning, submitted, Oct. 2023.
  2. Q. Yang, A. Sadeghi, G. Wang, and J. Sun,“Robust PSSE Using Graph Neural Networks for Data-driven and Topology-aware Priors.” IEEE Journal on Emerging and Selected Topics in Circuits and Systems, vol. 12, no. 1, pp. 172-181, March 2022.
  3. A. Sadeghi*, Q. Yang*, and G. Wang, “Learning Two-layer ReLU Networks is as Easy as Learning Linear Classifiers on Separable Data.” IEEE Transactions on Signal Processing, vol. 69, no. 1, pp. 4416–4427, July 2021.
  4. Q. Yang, G. Wang, A. Sadeghi, G. B. Giannakis, and J. Sun, “Two-Timescale Voltage Control in Distribution Grids using Deep Reinforcement Learning,” IEEE Transactions on Smart Grid, vol. 11, no. 3, pp. 2313-2323, May 2020.
  5. A. Sadeghi, G. Wang, and G. B. Giannakis, “Deep Reinforcement Learning for Adaptive Caching in Hierar- chical Content Delivery Networks,” IEEE Transactions on Cognitive Communications and Networking, vol. 5, no. 4, pp. 1024-1033, Dec. 2019.
  6. A. Sadeghi, F. Sheikholeslami, Antonio. G. Marques, and G. B. Giannakis, “Reinforcement Learning for Adap- tive Caching with Dynamic Storage Pricing,” IEEE Journal on Selected Areas in Communications, vol. 37, no. 10, pp. 2267-2281, Oct. 2019.
  7. A. Sadeghi, F. Sheikholeslami and G. B. Giannakis, “Optimal and Scalable Caching for 5G Using Reinforce- ment Learning of Space-Time Popularities,” IEEE Journal of Selected Topics in Signal Processing, vol. 12, no. 1, pp. 180-190, Feb. 2018. (Nominated for IEEE Signal Processing Young Author Best Paper Award)
  8. M. Luvisotto, A. Sadeghi, F. Lahouti, S. Vitturi and M. Zorzi, “RCFD: A Novel Channel Access Scheme for Full-Duplex Wireless Networks Based on Contention in Time and Frequency Domains,” IEEE Transactions on Mo- bile Computing, vol. 17, no. 10, pp. 2381-2395, 1 Oct. 2018.

Conferences

  1. A. Sadeghi, Y Zhang, and G. B. Giannakis , “A Universal Approach to Robust Meta-learning”, under prepa- ration - Intl. Conf. Mach. Learn., Vienna, Austria, Jul. 2024.
  2. Y Zhang, A. Sadeghi, and G. B. Giannakis , “Meta-Learning Universal Priors Using Non-Injective Normaliz- ing Flows”, Intl. Conf. Learn. Rep., Vienna, Austria, May 2024.
  3. KD Polyzos, A. Sadeghi, et. al. , “Bayesian Active Learning for Sample Efficient 5G Radio Map Reconstruc- tion”, Proc. of INFOCOM Conf., Vancouver, Canada, May 2024.
  4. KD Polyzos, A. Sadeghi and G. B. Giannakis, “Bayesian Self-Supervised Learning Using Local and Global Graph Information”, Proc. of CAMSAP, Los Suenos, Costa Rica, Dec. 2023 Nominated for Best Paper Award.
  5. S Chen, C. A. Grambow, M. K. Elyaderani, A. Sadeghi, F. Fancellu, and T. Schaaf, “Investigating the Util- ity of Synthetic Data for Doctor-Patient Conversation Summarization”, Proc. of Interspeech, Ireland, Aug. 2023.
  6. A. Sadeghi and G. B. Giannakis, “Learning while Respecting Privacy and Robustness to Adversarial Dis- tributed Datasets”, IEEE European Signal Process. Conf., Belgrade, Serbia, pp. 802-806, Aug. 2022.
  7. B. Weng, J. Sun, A. Sadeghi, and G. Wang, “AdaPID: An Adaptive PID Optimizer for Training Deep Neu- ral Networks,” Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing, Singapore (Virtual), May 2022.
  8. B. Li, A. Sadeghi, and G. B. Giannakis, “Heavy Ball Momentum for Conditional Gradien,” Adv. Neural Inf. Process. Syst., (NeurIPS), Virtual, Dec. 2021.
  9. K. D. Polyzos, A. Sadeghi, Q. Lu, and G. B. Giannakis, “On-policy Reinforcement Learning via Ensemble Gaussian Processes for Resource Allocation,” Proc. of Asilomar Conf. on Signals, Systems, and Computers, Pacific Grove, CA, Oct. 31–Nov. 3, 2021.
  10. A. Sadeghi, M. Ma, B. Li, G. B. Giannakis, “Distributionally Robust Semi-Supervised Learning over Graphs,” Intl. Conf. Learn. Rep. (ICLR) workshop on responsible AI (safety, interpretability, robustness, and fairness), Vir- tual, May 8, 2021.
  11. Q. Yang, A. Sadeghi, G. Wang, G. B. Giannakis, and J. Sun, “Deep Policy Gradient for Reactive Power Control in Distribution Systems,” IEEE Intl. Conf. on Commun., Control, and Computing Tech. for Smart Grids, Tempe, AZ, Oct. 2020.
  12. Q. Yang, A. Sadeghi, G. Wang, G. B. Giannakis, and J. Sun, “Power System State Estimation Using Gauss- Newton Unrolled Neural Networks with Trainable Priors,” IEEE Intl. Conf. on Commun., Control, and Computing Tech. for Smart Grids, Tempe, AZ, Oct. 2020. (Invited paper)
  13. A. Sadeghi, G. Wang, G. B. Giannakis, “Hierarchical Caching via Deep Reinforcement Learning,” Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing, Barcelona, Spain, May 2020.
  14. A. Sadeghi, A. G. Marquez, and G. B. Giannakis, “Distributed Network Caching via Dynamic Program- ming,” Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing, Brighton, UK, May 2019.
  15. Q. Yang, A. Sadeghi, G. Wang, G. B. Giannakis, and J. Sun, “Two-Timescale Voltage Regulation in Distribu- tion Grids Using Deep Reinforcement Learning,” IEEE Intl. Conf. on Commun., Control, and Computing Tech. for Smart Grids, Beijing, China, Nov. 2019. (Invited paper)
  16. A. Sadeghi, F. Sheikholeslami, and G. B. Giannakis, “Optimal Dynamic Proactive Caching via Reinforcement Learning,” Proc. of IEEE Intl. Workshop on Signal Processing Advances in Wireless Communications, Greece, July 2018. (Invited paper)
  17. A. Sadeghi, F. Sheikholeslami, A. G. Marquez, and G. B. Giannakis, “Reinforcement Learning for 5G Caching with Dynamic Cost,” Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing, Calgary, Alberta, Canada, Apr. 2018. (Invited paper)
  18. A. Sadeghi, S. Ghavami, and G. B. Giannakis, “Performance Bounds of Estimators in Molecular Communi- cations under Structural Constraints,” Proc. of ACM Intl. Conf. on Nanoscale Computing and Communication, Washington-DC, USA, Sep. 2017.
  19. A. Sadeghi, M. Luvisotto, F. Lahouti, S. Vitturi and M. Zorzi, “Statistical QoS analysis of full duplex and half duplex heterogeneous cellular networks,” IEEE Intl. Conf. on Commun., Kuala Lumpur, Malaysia, May 2016.
  20. A. Sadeghi, M. Zorzi and F. Lahouti, “Analysis of key generation rate from wireless channel in in-band full- duplex communications,” IEEE Intl. Conf. on Commun. Workshops, Kuala Lumpur, Malaysia, May 2016.
  21. M. Luvisotto, A. Sadeghi, F. Lahouti, S. Vitturi and M. Zorzi, “RCFD: A frequency-based channel access scheme for full-duplex wireless networks,” IEEE Intl. Conf. on Commun., Kuala Lumpur, Malaysia, May 2016.
  22. A. Sadeghi, F. Lahouti and M. Zorzi, “Constellation Shaping and LDPC Coding in a Bidirectional Full Du- plex Communication,” IEEE Global Communications Conference, San Diego, CA, USA, Dec. 2015.
  23. A. Rahmati, A. Sadeghi and V. Shah-Mansouri, “Price-based resource allocation for full duplex self-backhauled small cell networks,” IEEE Intl. Conf. Commun., London, United Kingdom, June 2015.

US Patents

  1. A. Sadeghi, et. al.: “Unsupervised Alignment of Machine-Generated Text with Input Data,” submitted 2023.
  2. J. D. Gandrud, K. W. Kampshoff, J. C. Dingeldein, J. Huang, S. A. H. Hosseini, A. Sadeghi, et. al.: “Auto- mated Processing of Oral Care Scans for Oral Care Appliance creation,” submitted 2023.
  3. M. K. Elyaderani, A. Sadeghi, et. al.: “A Re-ranking approach to Text Quality Prediction,” submitted 2023.
  4. P. Kumar, A. Sadeghi, S. A. Noghabi, S. Iyengar, S. Kalyanaraman, R. Chandra. Value Stacking: “Time Shifting in Power Grids to Use Under-utilized Power Storage,” submitted 2022.

Honors and awards

  1. Doctoral Dissertation Fellowship, University of Minnesota, UMN, USA
  2. ADC Graduate Fellowship, University of Minnesota, UMN, USA
  3. Nominated for IEEE-Signal Processing Young Author Best Papaer Award for paper [J7]
  4. NSF and IEEE-Communication Society (ComSoc) student travel awards
  5. Ranked 1st, Electrical Engineering, Iran University of Science & Technology
  6. Ranked 3rd, Engineering graduate students, University of Tehran

Services

Journals

  1. IEEE Journal of Selected Topics in Signal Processing
  2. IEEE Transactions on Signal Processing
  3. IEEE Journal on Selected Areas in Communications
  4. IEEE Transactions on Cognitive Com- munications and Networking
  5. IEEE Transactions on Mobile Computing
  6. IEEE Transactions on Wireless Communications
  7. IEEE Transactions on Communications
  8. IEEE Communications Letters;
  9. IEEE Wireless Communication Letters

Conferences

  1. International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  2. Internation conference on learning and representation (ICLR)
  3. Neural Information Processing Systems (NeurIPS)
  4. International Workshop on In- formation Theory (ITW)
  5. International Conference on Communications (ICC)
  6. Signal Processing Advances for Wireless Communications (SPAWC)
  7. European Wireless Communication Conference (EW)