Yahya Sattar

Yahya Sattar 5th year PhD student Department of Electrical and Computer Engineering University of California Riverside, CA 92521, USA email: ysatt001@ucr.edu

Bio

I am a PhD scholar at the University of California, Riverside (UCR) in the Optimization for Machine Learning Lab, the Department of Electrical and Computer Engineering (ECE), under the supervision of Samet Oymak. My research interests broadly lie in machine learning, statistical learning, non-convex optimization, reinforcement learning and data-driven control. I obtained my BSc in electrical engineering from Syed Babar Ali School of Science and Engineering (SBASSE) at LUMS. Prior to joining UCR, I worked as a research assistant in the Smart Data, Systems and Applications Lab at LUMS from September 2015 to June 2017. I have received the Deans Distinguished Fellowship Award at the University of California, Riverside (UCR) for the terms Fall 2017 - Spring 2018.

Research Interests

• Machine learning

• Statistical Learning

• Non-convex Optimization

• Reinforcement Learning

• Data-driven Control

Experience and Affiliation

Graduate Research Assistant Department of ECE, UCR, Jun 2018 – Present Graduate Teaching Assistant Department of ECE, UCR, Sep 2018 – Present EE-260: Introduction to Deep Learning (Spring 2020) EE-215: Stochastic Processes (Fall 2018 & Fall 2019) EE-114: Probability, Random Variables, and Random Processes (Spring 2019 & Winter 2020)

Research Assistant Department of EE, LUMS, Sep 2015 – Jun 2017

Graduate Student Member IEEE, IEEE Signal Processing Society

Education

• Ph.D. in Electrical & Computer Engineering
  University of California, Riverside
  Advisor: Samet Oymak
  Sep 2017 – Present

• B.Sc. in Electrical Engineering
  Lahore University of Management Sciences
  Sep 2011 – Jun 2015

Representative Publications

Journal Articles

• Non-Asymptotic and Accurate Learning of Nonlinear Dynamical System
  Journal of Machine Learning Research (JMLR), 2022

• Identification and Adaptive Control of Markov Jump Systems: Sample Complexity and Regret Bounds
  Journal of Machine Learning Research (JMLR), 2022
  Short version presented at ICML Workshop on Reinforcement Learning Theory, 2021

• Quickly finding the best linear model in high dimensions via projected gradient descent
  IEEE Transactions on Signal Processing (TSP), 2020

Conference Proceedings

• Data-driven Control of Markov Jump Systems: Sample Complexity and Regret Bounds
  IEEE American Control Conference (ACC), 2022
  

• Certainty Equivalent Quadratic Control for Markov Jump Systems
  IEEE American Control Conference (ACC), 2022
  

• A Simple Framework for Learning Stabilizable Systems
  IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2019
  

[Full list of publications]