Na
-
I am a Gordon McKay Professor of Electrical Engineering and Applied Mathematics in the School of Engineering and Applied Sciences (SEAS) at Harvard University and a research affiliate in Laboratory for Information and Decision Systems (LIDS) at Massachusetts Institute of Technology. I am also Cofounder and Chief Scientific Advisor of Singularity Energy, Inc, featuring the product of Carbonara which provides a suite of innovative products, developer APIs, and intelligent tools for companies to build the future of decarbonization solutions.
My research lies in the learning, optimization, and control of network systems, with particular applications to cyber-physical systems. The goal is to develop foundational decision-making tools to explore and exploit real-world system structures that can lead to computationally efficient and distributed solutions and apply them to improve systems operations and architecture. My research has been interdisciplinary in nature, integrating various mathematical, computational, engineering and some economics tools. I have received McDonald Mentoring Award, Donald P. Eckman Award, ONR YIP Award, AFOSR YIP Award, NSF CAREER Award, Harvard Climate Change Solution Fund, Harvard PSE Accelerator Award, CDC best student paper award finalist, CCTA best student paper award finalist (as an adviser) etc.
Google scholar page.
Latest News
- 08/2020: I am honored to receive IFAC Manfred Thoma Medal, which recognizes outstanding contributions of a young researcher and/or engineer under the age of 40 to the field of systems and control in its widest sense.
- 07/2022: Our paper "Escaping High-order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG) Control" was accepted to CDC.
- 06/2022: Our former Ph.D. student, Yingying Li, will start her tenure-track assistant professor position at UIUC in Fall 2023. Congratulations, Yingying!
- 05/2022: Our paper "Improve Single-Point Zeroth-Order Optimization Using High-Pass and Low-Pass Filters" was accepted to ICML.
- 02/2022: Our review paper "Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges" was accepted to IEEE Transactions on Smart Grids.
- 01/2022: Our paper "System-level, Input-output and New Parameterizations of Stabilizing Controllers, and Their Numerical Computation'' was accepted to Automatica.
- 11/2021: Xin Chen received the outstanding student paper award for our CDC paper, Model-Free Optimal Voltage Control via Continuous-Time Zeroth-Order Methods! Congratulations to Xin! Check our work at the coming CDC!
- 11/2021: Congratulations to our alumnus Jorge Poveda, for receiving the AFOSR YIP award!
- 11/2021: A new paper on Safe learning-based control, "Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees".
- 10/2021: A new paper on stochastic games ``Gradient play in stochastic games: stationary points, convergence, and sample complexity.
- 09/2021: Our former PhD student, Guannan Qu, will start his tenure-track assistant professor position at CMU. Congratulations, Guannan!
- 08/2021: Our team received the NSF award for ourNSF AI institute in Dynamical Systems! Check our institute website and press release for more details. My group will lead the thrust of AI for control.
- 07/2021: Our former postdoc, Yang Zheng, has started his tenure-track assistant professor position at UCSD. Congratulations, Yang!
- 06/2021: Our paper of ''Source Seeking by Dynamic Source Location Estimation'' was accepted to IROS 2021.
- 06/2021: Our paper of "Online Learning and Distributed Control for Residential Demand Response" was accepted to IEEE Transactions on Smart Grids.
- 03/2021: Our paper of "Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach" was conditionally accepted to IEEE Transactions on Automatic Control.
- 03/2021: Two papers related to learning for LQG were accepted to L4DC, including one oral presentation (top 10%)
- Analysis of the Optimization Landscape of Linear Quadratic Gaussian (LQG) Control. (Oral presentation)
- Sample Complexity of Linear Quadratic Gaussian (LQG) Control for Output Feedback Systems
- 03/2021: Our paper on "Leveraging Two-Stage Adaptive Robust Optimization for Power Flexibility Aggregation" is accepted to IEEE Transactions on Smart Grids.
- 02/2021: Our review paper on RL for power system is available: Reinforcement Learning for Decision-Making and Control in Power Systems: Tutorial, Review, and Vision
- 01/2021: Two ACC papers were accepted.
- On the Regret Analysis of Online LQR Control with Predictions
- LQR with Tracking: A Zeroth-order Approach and Its Global Convergence
- 12/2020: Our paper of "Federated Learning over Wireless Networks: A Band-limited Coordinated Descent Approach", was accepted to IEEE INFOCOM 2021.
- 12/2020: Our paper of "Online Optimal Control with Affine Constraints" was accepted to AAAI-21.
- 11/2020: Our paper: Non-asymptotic Identification of Linear Dynamical Systems Using Multiple Trajectories was accepted for publication in the IEEE Control Systems Society Letters (L-CSS).
- 11/2020: Our paper of "Online Optimization with Predictions and Switching Costs: Fast Algorithms and the Fundamental Limit" was accepted to IEEE Transaction on Automatic Control.
- 09/2020: Our paper of "On Maintaining Linear Convergence of Distributed Learning and Optimization under Limited Communication" was accepted to IEEE Transactions on Signal Processing.
- 09/2020: New NSF Award:CPS: Medium: An AI-enabled Cyber-Physical-Biological System for Cardiac Organoid Maturation
- 09/2020: New NSF Award: Collaborative Research: MLWiNS: Distributed Learning over Multi-Access Channels: From Bandlimited Coordinate Descent to Gradient Sketching
- 09/2020: Two papers were accepted to NeurIPS 2020,
- "Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward".
- "Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms".
- 09/2020: Our paper of "Robust Hybrid Zero-Order Optimization Algorithms with Acceleration via Averaging in Time" was accepted to Automatica.
- 08/2020: Our paper "Distributed Automatic Load Frequency Control with Optimality in Power Systems" was accepted for publication in IEEE Transactions on Control of Network Systems.
- 08/2020: Our paper of " Zeroth-Order Feedback Optimization for Cooperative Multi-Agent Systems" was accepted to CDC 2020.
- 07/2020: Our paper of "Semi-Global Exponential Stability of Augmented Primal-Dual Gradient Dynamics for Constrained Convex Optimization" was accepted to System and Control Lettters.
- 06/2020: Our paper of "Online Residential Demand Response via Contextual Multi-Armed Bandits" was accepted to IEEE Control Systems Letters. It will also be presented on CDC 2020.
- 05/2020: I received Capers W. McDonald and Marion K. McDonald Award for Excellence in Mentoring and Advising.
- 05/2020: Darrel Huang's senior thesis of "Teleoperation of Multi-Robot Systems Using Gesture-Based Control" won Dean's design awards honorable mention. Congratulation, Darrell!
- 04/2020: Our paper of "Distributed Zero-Order Algorithms for Nonconvex Multi-Agent Optimization" was conditionally accepted to IEEE Transactions on Control of Network systems.
- 03/2020: I was prompted as Gordon McKay Professor of Electrical Engineering and Applied Mathematics, effective July 1, 2020.
- 03/2020: Our paper of "A Reliability-aware Multi-armed Bandit Approach to Learn and Select Users in Demand Response" was accepted to Automatica.
- 02/2020: Our paper of "On the equivalence of Youla, System-level and Input-output parameterizations" was accepted to IEEE Transactions on Automatic Control.
- 01/2020: Two papers were accepted to IEEE Transactions on Smart Grid, 1) "Distributed Optimal Voltage Control with Asynchronous and Delayed Communication", 2) "A Market Mechanism for Virtual Inertia".
- 12/2019: New paper on "Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach" in a linear dynamical system setting. Related slides are here.
- 12/2019: New paper on "Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems" in an MDP (Markov Decision Process) setting. This follows our preliminary CDC work on multi-agent MDP. Related slides are here.
- 09/2019: Our paper of " "Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis" was accepted to NeurIPS 2019.
Source: https://nali.seas.harvard.edu/
0 Response to "Na"
Publicar un comentario