Hi! I'm Hamed Omidvar.

I am a PhD Candidate in the Electrical and Computer Engineering (ECE) Department at UC San Diego. I started my PhD program at UCSD in 2014 when I got the ECE departmental fellowship. My advisor is Prof. Massimo Franceschetti. I enjoy solving problems and I have worked on a variety of them. My recent works are on the compression and acceleration of Machine Leraning algorithms especially for large scale distributed training and/or inference and training on embeded devices. My PhD dissertation is about the analysis of the transient and steady state of self-organized behaviors in an interacting particle system (which can also be though of as an Asynchronous Cellular Automata) for which I was awarded the Shannon Memorial Fellowship in 2017. I am interested in probability theory and I use percolation theory in my works. I have also worked on other Machine Learning related problems. In the past I have worked on advanced scheduling / decision making mechanisms using POMDPs (Partially Observable Markov Decision Processes) for wireless networks, specifically for MAC layer of wearable devices while I was studying towards my master's degree in Sharif University of Technology. I received the Outstanding Graduate Student of the Year award in 2013.

My Resume.



I have a B.S. degree in Electrical Engineering - Electronics.



An M.Sc. degree in Electrical Engineering - Communication Systems from Sharif University of Technology.



And I am a Ph.D. Candidate in the Electrical and Computer Engineering department at UC San Diego.

Publications.

"Do not go where the path may lead, go instead where there is no path and leave a trail." -Ralph Waldo Emerson

  • Associative Convolutional Layers, Proceedings of International Conference on Artificial Intelligence and Statistics - 2021, H. Omidvar, V. Akhlaghi, H. Su, M. Franceschetti, and R. Gupta, Link: arXiv, Code: GitHub

  • Improved Intolerance Intervals and Size Bounds for a Schelling-Type Spin System, In preparation, Link: arXiv

  • Evolution and Steady State of a Long-Range Two-Dimensional Schelling-Type Spin System, In preparation, Link: arXiv

  • Shape of Diffusion and Size of Monochromatic Region of a Two-Dimensional Spin System, Proceedings of ACM Symposium on Theory of Computing (STOC) - 2018, Link: ACM

  • Self-organized Segregation on the Grid, Journal of Statistical Physics, H. Omidvar, M. Franceschetti – Springer

  • Self-organized Segregation on the Grid, Proceedings of ACM Symposium on Principles of Distributed Computing, H. Omidvar, M. Franceschetti – July 2017, Link: ACM, arXiv

  • An Energy-Efficient Multi-Sensor Scheduling Mechanism with QoS Support for WBANs – WCNC, H. Omidvar, F. Ashtiani, T. Javidi, M. Nasiri-Kenari, B. Vosoughi-Vahdat – April 2014

  • Failure Risk Assessment of Interdependent Infrastructures against Earth- quake, A Petri Net approach. Case study: Power and water distribution networks -- Springer’s Natural HazardsB. Omidvar, M. Hojjati, H. Omidvar – Dec. 2013

  • Simulation of Seismic Failure of Water Distribution Networks. Case Study: Water Distribution of Islamshahr – 6th  International Conference on Seismology and Earthquake EngineeringB. Omidvar, M. Hojjati, H. Omidvar – May 2011

Contact.

My email address is homidvar [at] ucsd [dot] edu
My office is located at Atkinson Hall, 4th Floor, 9500 Gilman Dr., La Jolla, CA 92093

Send Me an Email

Find me on ...