|
Research interests
Trustworthy AI
Develop data-driven technology that can be trusted to do the critical work
CPS Security
Protect the critical infrastructure against cyber and physical attacks
Human-centric Technology
Design methods that respect human-centric needs and values
Future Energy Systems
Ensure sustainable and reliable access to power and energy for society
Selected Awards
- Siebel Scholar (class of 2018)
- Best paper award, Building and Environment (2018)
- Best paper runner-up award at MobiQuitous (2016)
- Best paper award at Ubicomm for Mobile Ubiquitous Computing (2015)
News
Jan 2021Paper on online nonconvex optimization "Diminishing Regret for Online Nonconvex Optimization" to appear in 2021 American Control Conference
Jan 2021I will teach ECE5984 Special topic: Optimization Theory for ML (spring, 2021)
Dec 2020New paper on safe imitation learning "Imitation Learning with Stability and Safety Guarantees" (arXiv)
Dec 2020Paper on power grid cybersecurity "Boundary Defense Against Cyber Threat for Power System State Estimation" (pdf) to appear in IEEE Transactions on Information Forensics & Security
Dec 2020Paper on reinforcement learning "Stability-certified reinforcement learning: A control-theoretic perspective" to appear in IEEE Access
Dec 2020Paper on robust graph convolutional network "Power up! Robust Graph Convolutional Network via Graph Powering" accepted to AAAI 2021
Sep 2020See here a 5-minutes introduction to my research presented at the Engineering Faculty organization (EFO) faculty meeting, Virginia Tech
Sep 2020Paper on reinforcement learning for building control to appear in ACM International Workshop on Reinforcement Learning for Energy Management (RLEM'20) "Towards Off-policy Evaluation as a Prerequisite for Real-world Reinforcement Learning in Building Control"
Sep 2020Invited presentation at the 2020 CPES & PEC conference on "Adversarially robust learning and control for power grid"
Aug 2020Paper on deep learning for smart inverter control to appear in IEEE SmartGridComm'20 "Deep Learning for Reactive Power Control of Smart Inverters under Communication Constraints"