Ming Jin

I am an assistant professor in the Bradley Department of Electrical and Computer Engineering at Virginia Tech. I am also affiliated with the Power and Energy Center and Autonomy and Robotics @ VT. I work on interdisciplinary problems in optimization, learning theory, control, and cyber-physical systems.

I received my PhD in Electrical Engineering and Computer Science from UC Berkeley and BEng (honors) in Electronic and Computer Engineering from the Hong Kong University of Science and Technology. I was a postdoc in Industrial Engineering and Operations Research at UC Berkeley.

  ·     ·     ·     ·  


Research interests

Selected Awards

  • 1st Place Winner of the 2021 CityLearn Challenge (2021)
  • Siebel Scholar (class of 2018)
  • Best paper award, Building and Environment (2018)
  • Best paper runner-up award at EAI MobiQuitous (2016)
  • Best paper award at UBICOMM (2015)


News

Mar 2022

Paper on general bi-level optimization "Iterative Implicit Gradients for Nonconvex Optimization with Variational Inequality Constraints"

Mar 2022

Thanks The Commonwealth Cyber Initiative (CCI) for supporting our research

Mar 2022

Presentation at PMS 406 Autonomy MRE workshop on assured RL for dynamical systems

Feb 2022

Paper on learning under specifications "Learning Neural Networks under Input-Output Specifications" (arXiv) to appear in ACC 2022

Jan 2022

Paper on adversarial ML "Adversarial Unlearning of Backdoors via Implicit Hypergradient" (arXiv) accepted to ICLR 2022

Dec 2021

Paper on safe RL "Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems" (arXiv) to appear in AAAI 2022

Dec 2021

Paper on control by proxy "Controlling Smart Inverters using Proxies: A Chance-Constrained DNN-based Approach" (arXiv) to appear in IEEE Transactions on Smart Grid

Nov 2021

Thanks 4-VA for supporting our research

Nov 2021

Two teams that I led (ROLEVT & ZoRL) jointly won the 1st place in the CityLearn Challenge 2021. Congrats to team members: Vanshaj Khattar, Qasim Wani, Zhiyao Chang, and Mingyu Kim

Nov 2021

New paper on adversarial ML "Adversarial Unlearning of Backdoors via Implicit Hypergradient" (arXiv)

Nov 2021

Talk on assured RL for energy systems at C3.ai Digital Transformation Institute (video)

Oct 2021

My group will give an oral presentation on implicit RL in SECC 2021

Oct 2021

New paper on implicit RL "Zeroth-Order Implicit Reinforcement Learning for Sequential Decision Making in Distributed Control Systems"

Oct 2021

New paper on assured learning of neural networks "Learning Neural Networks under Input-Output Specifications"

Sep 2021

New paper on dynamic regret for online optimization "Dynamic Regret Bounds for Online Nonconvex Optimization"

Sep 2021

New paper on safe reinforcement learning "Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems" (arXiv)

... see all News