Abstract: As in extremum seeking, the conflict between exploration and exploitation arises also in adaptive control. The celebrated narrative for this conflict is in the adaptive control chapter of Feldbaum’s 1965 book on optimal control, the origin of the “dual control” conflict. Adaptive optimal control (adaptive LQR and dynamic programming) of the last couple of decades, often fueled by neural networks, avoids this challenge by seeking optimal gains as time approaches infinity - namely, by abandoning optimality, except in name. In 1997 and 2008 papers I introduced an approach to resolving the optimal exploration-exploitation conflict, in an inverse optimal sense. The essence is to penalize the parameter estimation error in an exponential-of-square (deterministic risk-sensitive) sense, while the state and control are penalized just quadratically. I.e., an adaptive controller must prioritize learning in order to be infinite-horizon optimal. Nonholonomic adaptive stabilization, developed in late 2025, provides the most interesting and most interpretation-friendly, to date, solution to the problem of optimal adaptive control. 

Bio: Miroslav Krstić is professor at UC San Diego, editor-in-chief of IEEE Transactions on Automatic Control, and a coauthor of several hundred journal articles and 19 books on adaptive, nonlinear, PDE, and extremum seeking control. His recognitions include the IEEE Brockett Control Systems Award, Bode Lecture Prize, Bellman Award, SIAM Reid Prize, ASME Oldenburger Medal, several awards from IFAC TCs, as well as the Chestnut Textbook Prize and Ragazzini Education Award. 

Abstract: We consider the intersection between feedback-based control and distributed Nash equilibrium (G)NE seeking algorithms. Unlike feedback-based optimization problems, we consider multiple independent decision makers (agents) with inherently coupled cost functions. In this case the algorithms take the form of dynamic feedback controllers that steer the agents’ actions to the NE of the game. We first present a general framework for solving Nash equilibrium seeking when agents have dynamics, subject to constant external disturbances. The framework consists of breaking down the design using a four-part control methodology. We show that the problem is reduced to the design of a set of decentralized stabilizing controllers. We solve the problem on a single timescale, i.e., stabilization and optimization happen simultaneously. This is complementary to a stabilize-then-optimize approach, whereby a prestabilized plant is interconnected with a slow sampled-data controller to drive the system the NE. In the second part of the talk, we consider a modification of the problem wherein each agent’s objective additionally depends on the measurable output of a nonlinear input-output mapping. We discuss how operator-theoretic methods can be leveraged to develop online distributed algorithms for this class of problems. 

Bio: Lacra Pavel received the Diploma of engineering from the Technical University of Iasi, Romania, and the Ph.D. degree from Queen’s University, Kingston, Canada in electrical engineering. She has been with the University of Toronto since 2002, where she is a Professor in the Department of Electrical and Computer Engineering. She is the author of the book “Game Theory for Control of Optical Networks” (Birkhauser/Springer). Her research interests are in game theory and optimization in networks, with emphasis on dynamics and control. She is an IEEE Fellow. She is the Editor-in-Chief for IEEE Transactions on Control of Networked Systems, and an Associate Editor for IEEE Transactions on Automatic Control. 

Abstract: Solving optimization problems in dynamic environments is a pervasive objective in engineering applications, encompassing problems such dynamic model training in machine learning, target tracking in image processing, system optimization in industrial control, and portfolio optimization in finance. The need for online solutions that can adapt to dynamic performance metrics and system constraints has sparked the development of the flourishing research area known as online optimization. This presentation introduces a novel approach to designing online optimization algorithms by leveraging concepts from the internal model principle of control theory. By reframing optimization design objectives as output regulation problems, we will establish a design methodology that provides a systematic framework for conceptualizing new optimization algorithms. This approach is poised to revolutionize traditional optimization-driven designs, offering a fresh perspective on tackling time-varying optimization challenges. The presentation will cover illustrative applications and aims at providing an overview of open questions and challenges in the area.

Bio: Gianluca Bianchin is an Assistant Professor with the ICTEAM Institute at the University of Louvain (UCLouvain), Belgium. He received the Ph.D. degree in Mechanical Engineering from the University of California Riverside in 2020. He previously obtained the M.Sc. degree in Controls Engineering from the University of Padua, Italy, in 2014. Dr. Bianchin was a Postdoctoral Scholar in the Department of Electrical, Computer, and Energy Engineering at the University of Colorado Boulder from 2020 to 2022. He has also spent time as a Visiting Researcher at the Bosch Research and Technology Center North America and at the Pacific Northwest National Laboratory. Prof. Bianchin received the IEEE Transactions on Control of Network Systems Best Paper Award in 2023 and the Dissertation Year Award from the University of California, Riverside, in 2019. Additionally, his research on secure robotic navigation was selected as the Editor’s Choice of the Month by the Elsevier journal Automatica in February 2020. His research interests include dynamical systems, control theory, and algorithmic optimization and their applications in traffic control and network infrastructures.

Abstract: Critical infrastructure systems, including energy communities, process industries, and manufacturing networks, are increasingly operated by multiple decision-making entities sharing common resources. Efficient coordination of such interconnected systems demands real-time schemes that are both principled and provably well-behaved. This workshop develops two complementary paradigms spanning the gradient information spectrum: from first-order feedback optimizing control, to zeroth-order Bayesian optimization. A central theme is generalizability: both paradigms yield generalizable architectures, derived from optimization principles, that can be directly instantiated across diverse canonical problem classes. For feedback optimizing control, we present a systematic methodology for transforming optimality conditions into structured, closed-loop control architectures. Convergence guarantees are established under realistic assumptions, bridging steady-state optimization theory with dynamic feedback design, with the main aim of exposing principled guidelines for tuning, transient behavior, and performance trade-offs. For the data-driven setting, we develop a general-purpose Bayesian optimization framework tailored to interconnected systems, accompanied by rigorous regret analysis to understand how the coordination terms might affect regret in the generalized setting.

Bio: Dinesh Krishnamoorthy is an Associate professor at the Department of Engineering Cybernetics at Norwegian University of Science and Technology (NTNU). From 2022 - 2025, he was an Assistant Professor at the Department of Mechanical Engineering at TU Eindhoven, and between 2021-2022, he was a post-doctoral researcher at Harvard John A. Paulson School of Engineering and Applied Sciences. Dinesh received his PhD in Process Systems Engineering from NTNU, MSc in Control Systems from Imperial College London, and B.Eng in Mechatronics from the University of Nottingham. Dinesh was a recipient of the Dimitirs. N. Chorafas Foundation Award, EuroTech Future Award, as well as a IFAC Young author award. His research interests include distributed optimization, learning-based optimal control, real-time optimization, and Bayesian optimization. 

Abstract: Reliable data-driven control must provide closed-loop guarantees—on stability, performance, safety—by generalizing across an entire domain from finite samples of the dynamics. In learning theory, this is usually achieved via the introduction of an inductive bias, that is, a set of structural assumptions placed on the problem to connect sampled and unsampled data. While inductive biases for classification and regression problems have been widely studied and their performance is well understood, much less is known for control tasks. This raises a central question: which inductive bias enables efficient nonlinear control with rigorous guarantees on stability, safety, and optimality?

For Lipschitz continuous vector fields, a common assumption (or inductive bias) in control, we construct behavioral guarantees by combining local improvement conditions—integral Lyapunov-like conditions or Bellman inequalities—with coverage arguments over the state space that render such behavior recurrent. This viewpoint enables data-driven verification, but also inspires a novel class of nonparametric controllers, called here chain policies, which are akin to action chunking but with variable duration, and compose a sequence of locally verified controls (a chain) into globally valid certifiable policies. We apply these ideas to data-driven stabilization and to the acceleration of model predictive control, where performance can be systematically traded for reduced data requirements.

Notably, this Lipschitz viewpoint, while flexible, is very conservative: its worst-case bounds still require dense coverage of the state space, a demand that scales poorly with state dimension. To overcome this limitation, we turn to Hamiltonian dynamics, which offer a structurally different inductive bias based on energy and volume conservation. These conservation laws imply, via the Poincaré recurrence theorem, that every region visited by a trajectory is revisited infinitely often, providing vast opportunities for generalization. This allows us to construct chain policies for target reachability from remarkably small datasets.

Bio: Enrique Mallada is an Associate Professor of Electrical and Computer Engineering at Johns Hopkins University, where he has been a faculty member since 2016. He received his Ph.D. in Electrical and Computer Engineering with a minor in Applied Mathematics from Cornell University and a Telecommunications Engineering degree from ORT University, Uruguay. Before joining Hopkins, he was a Postdoctoral Fellow at Caltech’s Center for the Mathematics of Information. His honors include the Johns Hopkins Alumni Association Teaching Award (2021), NSF CAREER Award (2018), Caltech’s CMI Fellowship (2014), and Cornell ECE Director’s Thesis Award (2014). His research spans control, dynamical systems, and optimization, with applications to safety-critical systems, networks, and power grids.

Abstract: Hierarchical decision-making problems, such as bilevel programs and Stackelberg games, are attracting increasing interest in both the engineering and machine learning communities; yet existing solution methods often lack either convergence guarantees or computational efficiency due to the absence of smoothness and convexity. In this talk, we bridge this gap by presenting a first-order hypergradient-based algorithm for Stackelberg games and by mathematically establishing its convergence using tools from nonsmooth analysis and automatic control. To evaluate the hypergradient, namely the gradient of the upper-level objective, we develop an online scheme that simultaneously computes the lower-level equilibrium and its Jacobian. We demonstrate BIG Hype’s potential by deploying it on various large-scale incentive-design problems, including demand-response in smart grids, traffic routing, and reactive power procurement.

Bio: Giuseppe Belgioioso (Member, IEEE) is an Assistant Professor at the Department of Decision and Control Systems at KTH Royal Institute of Technology, Sweden. He received the bachelor’s degree in information engineering in 2012 and the master’s degree (cum laude) in control systems engineering in 2015, both at the University of Padova, Italy. In 2020, he obtained the Ph.D. degree in Automatic Control at Eindhoven University of Technology (TU/e), The Netherlands. From 2021 to 2024, he was first a Postdoctoral researcher and then Senior Scientist at the Automatic Control Laboratory, ETH Z"{u}rich, Switzerland. His research lies at the intersection of optimization, game theory, and automatic control with applications in complex systems, especially electrical as power grids.

Abstract: Constrained optimization is fundamental to numerous safety-critical applications. While first-order iterative methods are commonly used, viewing these algorithms through their continuous-time limits—as differential equations—can yield valuable insights into stability and convergence. Among existing approaches, feedback linearization, a classical tool from nonlinear control, has recently shown promise for nonconvex constrained optimization, yet its theoretical foundations remain underexplored.

In this work, we develop a control-theoretic framework for constrained optimization based on feedback linearization. In the first-order setting, we establish global convergence rates to first-order KKT points and reveal a close connection to Sequential Quadratic Programming (SQP). Building on this connection, we extend the feedback linearization framework to the zeroth-order regime. Since zeroth-order methods rely on noisy, sample-based gradient estimates, ensuring constraint satisfaction is particularly challenging. We show that feedback linearization enables a family of zeroth-order algorithms that provably maintain feasibility despite noisy gradient information.

Bio: Na Li is a Winokur Family Professor of Electrical Engineering and Applied Mathematics at Harvard University.  She received her Bachelor's degree in Mathematics from Zhejiang University in 2007 and Ph.D. degree in Control and Dynamical systems from California Institute of Technology in 2013. She was a postdoctoral associate at the Massachusetts Institute of Technology 2013-2014.  She has held a variety of short-term visiting appointments including the Simons Institute for the Theory of Computing, MIT, Google Brain, and MERL. Her research lies in the control, learning, and optimization of networked systems, including theory development, algorithm design, and applications to real-world cyber-physical societal system.  She is an IEEE member and a senior editor of IEEE Transactions on Control of Network Systems. She was an associate editor for IEEE Transactions on Automatic Control, Systems & Control Letters, IEEE Control Systems Letters and also served on the organizing committee for a few conferences and workshops such as IEEE CDC, AMC E-energy, and NSF workshop on Reinforcement Learning.  She received the NSF career award, AFSOR Young Investigator Award, ONR Young Investigator Award,  Donald P. Eckman Award, McDonald Mentoring Award, IEEE CSS Distinguished Lecturer, IFAC Distinguished Lecturer, IFAC Manfred Thoma Medal, Ruberti Young Researcher Prize, along with other awards.

Abstract: The adjacent fields of reinforcement learning (RL) and adaptive control share the same objectives, yet they are separated by a wide cultural gap. In this presentation, I attempt to bridge this gap for the linear quadratic regulator (LQR) problem, which serves as a cornerstone and the benchmark for both fields. I begin by discussing different learning pipelines, including direct and indirect (model-based) approaches, as well as episodic and online (adaptive) approaches. Despite the extensive literature spanning several decades, numerous problems remain unsolved. For instance, RL methods are seldom concerned with closed-loop stability certificates or efficient implementations, while the adaptive control community has dedicated minimal effort to optimality. We address the data-driven LQR problem in an adaptive setting, which entails online recursive algorithms and closed-loop data, and we seek both algorithmic as well as closed-loop certificates. Our approach encompasses different variations of policy gradient methods and employs a novel covariance parameterization of the LQR problem. Finally, all our theoretical results are validated through simulations and experiments in diverse domains, demonstrating the computational and sample efficiency of our method.

Bio: Florian Dörfler is a Professor at the Automatic Control Laboratory at ETH Zürich. He received his Ph.D. degree in Mechanical Engineering from the University of California at Santa Barbara in 2013, and a Diplom degree in Engineering Cybernetics from the University of Stuttgart in 2008. From 2013 to 2014 he was an Assistant Professor at the University of California Los Angeles.  He is a recipient of the 2025 Rössler Prize, the highest scientific award at ETH Zürich across all disciplines, as well as the distinguished career awards by IFAC (Manfred Thoma Medal 2020) and EUCA (European Control Award 2020). He and his team   were recipients of the 2011 O. Hugo Schuck Best Paper Award, the 2012-2014 Automatica Best Paper Award, the 2016 IEEE Circuits and Systems Guillemin-Cauer Best Paper Award, the 2022 IEEE Transactions on Power Electronics Prize Paper Award, the 2024 Control Systems Magazine Outstanding Paper Award,  multiple Best PhD thesis awards at UC Santa Barbara and ETH Zürich, winners or finalists for Best Student Paper awards at the European Control Conference (2013, 2019), the American Control Conference (2010,2016,2024), the Conference on Decision and Control (2020), the PES General Meeting (2020), the PES PowerTech Conference (2017,2025), the International Conference on Intelligent Transportation Systems (2021), the IEEE CSS Swiss Chapter Young Author Best Journal Paper Award (2022,2024,2025), the IFAC Conferences on Nonlinear Model Predictive Control (2024) and Cyber-Physical-Human Systems (2024), and NeurIPS Oral (2024). He is a Fellow of the IEEE and currently serving on the council of the European Control Association and as a senior editor of Automatica.