|
Paper on certified robustness for neural ODE accepted in IEEE Control Systems Letters (L-CSS)
Mar 2023Paper on derivative-free meta blackbox (nonconvex) optimization on manifold at L4DC 2023 (oral presentation)
Mar 2023Two papers theoretical analysis of Sobolev training and decision-focused variational inequality at IFAC World Congress 2023
Feb 2023One paper adversarial ML (sifting out clean data from poisoned data) at USENIX Security 2023
Jan 2023Three papers on meta-safe reinforcement learning (spotlight), model-agnostic data valuation (spotlight), and adversarial ML (certified robustness against UAP/backdoors) at ICLR 2023
Nov 2022Three papers at AAAI on winning the CityLearn Challenge (oral), approximation/statistical properties of solution functions (oral), and nonstationary risk-sensitive RL (oral)
Jun 2022Paper on dynamic regret for online optimization "Dynamic Regret Bounds for Online Nonconvex Optimization" to appear in IEEE Transactions on Control of Network Systems
Mar 2022Paper on general bi-level optimization "Iterative Implicit Gradients for Nonconvex Optimization with Variational Inequality Constraints"
Mar 2022Thanks The Commonwealth Cyber Initiative (CCI) for supporting our research
Mar 2022Presentation at PMS 406 Autonomy MRE workshop on assured RL for dynamical systems
Feb 2022Paper on learning under specifications "Learning Neural Networks under Input-Output Specifications" (arXiv) to appear in ACC 2022
Jan 2022Paper on adversarial ML "Adversarial Unlearning of Backdoors via Implicit Hypergradient" (arXiv) accepted to ICLR 2022
Dec 2021Paper on safe RL "Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems" (arXiv) to appear in AAAI 2022
Dec 2021Paper 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 2021Two 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 2021New paper on adversarial ML "Adversarial Unlearning of Backdoors via Implicit Hypergradient" (arXiv)