Lessons from Adaptive Control: Towards Real-time Machine Learning

March 11, 2022, zoom

Anuradha Annaswamy

MIT, Mechanical Engineering


The fields of adaptive control and machine learning have evolved in parallel over the past few decades, with a significant overlap in goals, problem statements, and tools. Machine learning as a field has focused on computer based systems that improve through experience. Often times the process of learning is encapsulated in the form of a parameterized model such as a neural network, whose weights are trained in order to approximate a function. The field of adaptive control, on the other hand, has focused on the process of controlling engineering systems in order to accomplish regulation and tracking of critical variables of interest. Learning is embedded in this process via online estimation of the underlying parameters. Whether in machine learning or adaptive control, this learning occurs through the use of input-output data. In both cases, the main algorithm used for updating the parameters is based on a gradient descent-like algorithm. Related tools of analysis, convergence, and robustness in both fields have a tremendous amount of similarity. As the scope of problems in both topics increases, the associated complexity and challenges increase as well. In order to address learning and decision-making in real time, it is essential to understand these similarities and connections to develop new methods, tools, and algorithms. This talk will examine the similarities and interconnections between adaptive control and methods such as reinforcement learning. Concepts in stability, performance, and learning, common to both fields will be discussed. Building on the similarities in update laws and common concepts, new intersections and opportunities for improved algorithm analysis will be explored. High-order tuners and time-varying learning rates have been employed in adaptive control leading to very interesting results in dynamic systems with delays. We will explore how these methods can be leveraged and integrated to lead to provably correct methods for learning in real-time with guaranteed fast convergence. Examples will be drawn from a range of engineering applications.

Speaker's Bio

Dr. Anuradha Annaswamy is Founder and Director of the Active Adaptive Control Laboratory in the Department of Mechanical Engineering at MIT. Her research interests span adaptive control theory and its applications to aerospace, automotive, propulsion, and energy systems as well as cyber physical systems such as Smart Grids, Smart Cities, and Smart Infrastructures. She has received best paper awards (Axelby; CSM), as well as Distinguished Member and Distinguished Lecturer awards from the IEEE Control Systems Society (CSS) and a Presidential Young Investigator award from NSF. She is a Fellow of IEEE and International Federation of Automatic Control. She is the recipient of the Distinguished Alumni award from Indian Institute of Science for 2021. <br> Anu Annaswamy is the author of a graduate textbook on adaptive control, co-editor of two vision documents on smart grids as well as two editions of the Impact of Control Technology report, and a member of the National Academy of Sciences Committee study that published a report on the Future of Electric Power in the United States in 2021. She served as the President of CSS in 2020. She has been serving as a Faculty Lead in the Electric Power Systems workstream in the MIT Future Energy Systems Center since September 2021.