A central problem in machine learning is as follows: How should we train models using data generated from a collection of clients/environments, if we know that these models will be deployed in a new and unseen environment? In the setting of few-shot learning, two prominent approaches are: (a) develop a modeling framework that is “primed” to adapt, such as Model Adaptive Meta Learning (MAML), or (b) develop a common model using federated learning (such as FedAvg), and then fine tune the model for the deployment environment. We study both these approaches in the multi-task linear representation setting. We show that the reason behind generalizability of the models in new environments trained through either of these approaches is that the dynamics of training induces the models to evolve toward the common data representation among the clients’ tasks. In both cases, the structure of the bi-level update at each iteration (an inner and outer update with MAML, and a local and global update with FedAvg) holds the key — the diversity among client data distributions are exploited via inner/local updates, and induces the outer/global updates to bring the representation closer to the ground-truth. In both these settings, these are the first results that formally show representation learning and derive exponentially fast convergence to the ground-truth representation. This talk is based on joint work with Liam Collins, Hamed Hassani, Aryan Mokhtari, and Sewoong Oh.

Dr. Sanjay Shakkottai received his Ph.D. from the ECE Department at the University of Illinois at Urbana-Champaign in 2002. He is with The University of Texas at Austin, where he is a Professor in the Department of Electrical and Computer Engineering and holds the Cockrell Family Chair in Engineering #15. He received the NSF CAREER award in 2004 and was elected as an IEEE Fellow in 2014. He was a co-recipient of the IEEE Communications Society Willi.

The past four decades witnessed the birth and growth of neurodynamic optimization, which has emerged as a potentially powerful problem-solving tool for constrained optimization due to its inherent nature of biological plausibility and parallel and distributed information processing. Despite the success, almost all existing neurodynamic approaches a few years ago worked well only for optimization problems with convex or generalized convex functions. Effective neurodynamic approaches to optimization problems with nonconvex functions and discrete variables are rarely available. In this talk, the advances in neurodynamic optimization will be presented. Specifically, In the proposed collaborative neurodynamic optimization framework, multiple neurodynamic optimization models with different initial states are employed for scattered searches. In addition, a meta-heuristic rule in swarm intelligence (such as PSO) is used to reposition neuronal states upon their local convergence to escape local minima toward global optima. Several specific paradigms in this hybrid intelligence framework will be delineated for multi-objective and mixed-integer optimization. Experimental results will be elaborated to substantiate the efficacy of the methodology including an IoT-based application for distributed chiller loading.

Jun Wang is the Chair Professor of Computational Intelligence in the Department of Computer Science and School of Data Science at City University of Hong Kong. Prior to this position, he held various academic positions at Dalian University of Technology, Case Western Reserve University, University of North Dakota, and the Chinese University of Hong Kong. He also held various short-term visiting positions at USAF Armstrong Laboratory, RIKEN Brain Science Institute, Huazhong University of Science and Technology, Shanghai Jiao Tong University, and Swinburne University of Technology. He received a B.S. degree in electrical engineering and an M.S. degree from Dalian University of Technology and his Ph.D. degree from Case Western Reserve University. He was the Editor-in-Chief of the IEEE Transactions on Cybernetics. He is an IEEE Life Fellow, IAPR Fellow, and a foreign member of Academia Europaea. He is a recipient of the APNNA Outstanding Achievement Award, IEEE CIS Neural Networks Pioneer Award, CAAI Wu Wenjun AI Achievement Award, and IEEE SMCS Norbert Wiener Award, among other distinctions.

High-Confidence Computing (HCC) relies on interdisciplinary methodologies to realize secure and trusted software, precise and process-traceable algorithms, and self-evolving designs that can adapt to new environments and support new applications. Internet of Things (IoT) systems possessing HCC properties can provide collaborative services that are otherwise impossible as security, traceability, accountability, reliability, robustness, extensibility, adaptivity, and self-evolution are all desirable and equally-important properties of modern connected systems such as smart cities. This talk intends to answer the following questions: what is high-confidence computing and how to realize high-confidence IoT via blockchain technology. We will introduce an architecture to demonstrate our exploratory studies regarding how to integrate state-of-the-art techniques to build a blockchain-enabled high-confidence IoT and present our own effort towards its realization. Open research challenges will also be discussed.

Xiuzhen Cheng received her M.S. and Ph.D. degrees in Computer science from University of Minnesota, Twin Cities, in 2000 and 2002, respectively. She was a faculty member in the Department of Computer Science, George Washington University, from 2002 to 2020. Currently she is a professor of computer science at Shandong University. Her research focuses on blockchain computing, security and privacy, and the Internet of Things.

Solid-state lighting using LEDs offers new opportunities for visible light communications (VLC) and positioning (VLP). This keynote reviews recent advances in developing LED-based VLC/VLP technologies to support various smart internet-of-thing (IoT) systems and applications, including design examples.

Albert Wang is a Professor of Electrical and Computer Engineering at University of California, Riverside, USA. His research covers semiconductor devices, analog/mixed-signal and RF ICs, design-for-reliability for ICs, 3D heterogeneous integration, emerging devices and circuits, and LED visible light communications. He published two books and 310+ peer-reviewed papers, and holds sixteen U.S. patents. His editorial board services include IEEE Transactions on Circuits and Systems I, IEEE Electron Device Letters, IEEE Transactions on Circuits and Systems II, IEEE Transactions on Electron Devices, IEEE Journal of Solid-State Circuits, and IEEE Transactions on Device and Materials Reliability. He has been IEEE Distinguished Lecturer for IEEE Electron Devices Society, IEEE Circuits and Systems Society and IEEE Solid-State Circuits Society. He was President of IEEE Electron Devices Society. He served as a Program Director of the National Science Foundation, USA. He was recipient of IEEE J. J. Ebers Award. Wang is a Fellow of National Academy of Inventors and an IEEE Fellow.