arXiv subjects

Tamer Basar

Publications and source records attributed to Tamer Basar.

At least 19 recordsLinked to original sources

arXiv2026

Independent Reinforcement Learning in Discounted Markov Games

In this work, we study radically uncoupled learning in discounted general-sum Markov games. Assuming ``$\mathsf{ETH}$ for $\mathsf{PPAD}$", we show that, for every fixed discount factor, there is no polynomial-time algorithm for computing inverse-polynomially accurate coarse correlated equilibria in discounted general-sum Markov games when players learn independently in decentralized settings. Complementing this hardness result, we provide what appears to be the first \emph{radically uncoupled} algorithm with sub-exponential convergence guarantees to coarse correlated equilibria in discounted general-sum Markov games without imposing any structural restrictions on the game. Our algorithm is a \emph{layered} variant of optimistic mirror descent with an increasing step-size schedule tailored to the multi-agent setting. Finally, we develop both full-feedback and partial feedback versions of the aforementioned algorithm and establish sub-exponential convergence guarantees for each case.

cs.GT↗

arXiv2025

Distributed Event-Triggered Nash Equilibrium Seeking for Noncooperative Games

We propose locally convergent Nash equilibrium seeking algorithms for $N$-player noncooperative games, which use distributed event-triggered pseudo-gradient estimates. The proposed approach employs sinusoidal perturbations to estimate the pseudo-gradients of unknown quadratic payoff functions. This is the first instance of noncooperative games being tackled in a model-free fashion with event-triggered extremum seeking. Each player evaluates independently the deviation between the corresponding current pseudo-gradient estimate and its last broadcasted value from the event-triggering mechanism to tune individually the player action, while they preserve collectively the closed-loop stability/convergence. We guarantee Zeno behavior avoidance by establishing a minimum dwell-time to avoid infinitely fast switching. In particular, the stability analysis is carried out using Lyapunov's method and averaging for systems with discontinuous right-hand sides. We quantify the size of the ultimate small residual sets around the Nash equilibrium and illustrate the theoretical results numerically on an oligopoly setting.

math.OC↗

arXiv2025

Lie-Bracket Nash Equilibrium Seeking with Bounded Update Rates for Noncooperative Games

This paper proposes a novel approach for local convergence to Nash equilibrium in quadratic noncooperative games based on a distributed Lie-bracket extremum seeking control scheme. This is the first instance of noncooperative games being tackled in a model-free fashion integrated with the extremum seeking method of bounded update rates. In particular, the stability analysis is carried out using Lie-bracket approximation and Lyapunov's direct method. We quantify the size of the ultimate small residual sets around the Nash equilibrium and illustrate the theoretical results numerically on an example in an oligopoly setting.

math.OC↗

arXiv2024

Disentangling Resilience from Robustness: Contextual Dualism, Interactionism, and Game-Theoretic Paradigms

This article explains the distinctions between robustness and resilience in control systems. Resilience confronts a distinct set of challenges, posing new ones for designing controllers for feedback systems, networks, and machines that prioritize resilience over robustness. The concept of resilience is explored through a three-stage model, emphasizing the need for a proactive preparation and automated response to elastic events. A toy model is first used to illustrate the tradeoffs between resilience and robustness. Then, it delves into contextual dualism and interactionism, and introduces game-theoretic paradigms as a unifying framework to consolidate resilience and robustness. The article concludes by discussing the interplay between robustness and resilience, suggesting that a comprehensive theory of resilience and quantification metrics, and formalization through game-theoretic frameworks are necessary. The exploration extends to system-of-systems resilience and various mechanisms, including the integration of AI techniques and non-technical solutions, like cyber insurance, to achieve comprehensive resilience in control systems. As we approach 2030, the systems and control community is at the opportune moment to lay scientific foundations of resilience by bridging feedback control theory, game theory, and learning theory. Resilient control systems will enhance overall quality of life, enable the development of a resilient society, and create a societal-scale impact amid global challenges such as climate change, conflicts, and cyber insecurity.

eess.SY↗

arXiv2023

A Discrete-time Networked Competitive Bivirus SIS Model

The paper deals with the analysis of a discrete-time networked competitive bivirus susceptible-infected-susceptible (SIS) model. More specifically, we suppose that virus 1 and virus 2 are circulating in the population and are in competition with each other. We show that the model is strongly monotone, and that, under certain assumptions, it does not admit any periodic orbit. We identify a sufficient condition for exponential convergence to the disease-free equilibrium (DFE). Assuming only virus 1 (resp. virus 2) is alive, we establish a condition for global asymptotic convergence to the single-virus endemic equilibrium of virus 1 (resp. virus 2) -- our proof does not rely on the construction of a Lyapunov function. Assuming both virus 1 and virus 2 are alive, we establish a condition which ensures local exponential convergence to the single-virus equilibrium of virus 1 (resp. virus 2). Finally, we provide a sufficient (resp. necessary) condition for the existence of a coexistence equilibrium.

eess.SY↗

arXiv2023

Analysis, Control, and State Estimation for the Networked Competitive Multi-Virus SIR Model

This paper proposes a novel discrete-time multi-virus susceptible-infected-recovered (SIR) model that captures the spread of competing epidemics over a population network. First, we provide sufficient conditions for the infection level of all the viruses over the networked model to converge to zero in exponential time. Second, we propose an observation model which captures the summation of all the viruses' infection levels in each node, which represents the individuals who are infected by different viruses but share similar symptoms. Third, we present a sufficient condition for the model to be strongly locally observable, assuming that the network has only infected or recovered individuals. Fourth, we propose a Luenberger observer for estimating the states of our system. We prove that the estimation error of our proposed estimator converges to zero asymptotically with the observer gain. Finally, we present a distributed feedback controller which guarantees that each virus dies out at an exponential rate. We then show via simulations that the estimation error of the Luenberger observer converges to zero before the viruses die out.

eess.SY↗

arXiv2022

Decentralized Nonconvex Optimization with Guaranteed Privacy and Accuracy

Privacy protection and nonconvexity are two challenging problems in decentralized optimization and learning involving sensitive data. Despite some recent advances addressing each of the two problems separately, no results have been reported that have theoretical guarantees on both privacy protection and saddle/maximum avoidance in decentralized nonconvex optimization. We propose a new algorithm for decentralized nonconvex optimization that can enable both rigorous differential privacy and saddle/maximum avoiding performance. The new algorithm allows the incorporation of persistent additive noise to enable rigorous differential privacy for data samples, gradients, and intermediate optimization variables without losing provable convergence, and thus circumventing the dilemma of trading accuracy for privacy in differential privacy design. More interestingly, the algorithm is theoretically proven to be able to efficiently { guarantee accuracy by avoiding} convergence to local maxima and saddle points, which has not been reported before in the literature on decentralized nonconvex optimization. The algorithm is efficient in both communication (it only shares one variable in each iteration) and computation (it is encryption-free), and hence is promising for large-scale nonconvex optimization and learning involving high-dimensional optimization parameters. Numerical experiments for both a decentralized estimation problem and an Independent Component Analysis (ICA) problem confirm the effectiveness of the proposed approach.

math.OC↗

arXiv2022

Ensuring both Provable Convergence and Differential Privacy in Nash Equilibrium Seeking on Directed Graphs

We study in this paper privacy protection in fully distributed Nash equilibrium seeking where a player can only access its own cost function and receive information from its immediate neighbors over a directed communication network. In view of the non-cooperative nature of the underlying decision-making process, it is imperative to protect the privacy of individual players in networked games when sensitive information is involved. We propose an approach that can achieve both accurate convergence and rigorous differential privacy with finite cumulative privacy budget in distributed Nash equilibrium seeking, which is in sharp contrast to existing differential-privacy solutions for networked games that have to trade convergence accuracy for differential privacy. The approach is applicable even when the communication graph is unbalanced and it does not require individual players to have any global structure information of the communication graph. Since the approach utilizes independent noises for privacy protection, it can combat adversaries having access to all shared messages in the network. It is also encryption-free, ensuring high efficiency in communication and computation. Numerical comparison results with existing counterparts confirm the effectiveness of the proposed approach.

cs.GT↗

arXiv2022

Quantization enabled Privacy Protection in Decentralized Stochastic Optimization

By enabling multiple agents to cooperatively solve a global optimization problem in the absence of a central coordinator, decentralized stochastic optimization is gaining increasing attention in areas as diverse as machine learning, control, and sensor networks. Since the associated data usually contain sensitive information, such as user locations and personal identities, privacy protection has emerged as a crucial need in the implementation of decentralized stochastic optimization. In this paper, we propose a decentralized stochastic optimization algorithm that is able to guarantee provable convergence accuracy even in the presence of aggressive quantization errors that are proportional to the amplitude of quantization inputs. The result applies to both convex and non-convex objective functions, and enables us to exploit aggressive quantization schemes to obfuscate shared information, and hence enables privacy protection without losing provable optimization accuracy. In fact, by using a {stochastic} ternary quantization scheme, which quantizes any value to three numerical levels, we achieve quantization-based rigorous differential privacy in decentralized stochastic optimization, which has not been reported before. In combination with the presented quantization scheme, the proposed algorithm ensures, for the first time, rigorous differential privacy in decentralized stochastic optimization without losing provable convergence accuracy. Simulation results for a distributed estimation problem as well as numerical experiments for decentralized learning on a benchmark machine learning dataset confirm the effectiveness of the proposed approach.

math.OC↗

arXiv2022

A Networked Competitive Multi-Virus SIR Model: Analysis and Observability

This paper proposes a novel discrete-time multi-virus SIR (susceptible-infected-recovered) model that captures the spread of competing SIR epidemics over a population network. First, we provide a sufficient condition for the infection level of all the viruses over the networked model to converge to zero in exponential time. Second, we propose an observation model which captures the summation of all the viruses' infection levels in each node, which represents the individuals who are infected by different viruses but share similar symptoms. We present a sufficient condition for the model to be locally observable. We propose a Luenberger observer for the system state estimation and show via simulations that the estimation error of the Luenberger observer converges to zero before the viruses die out.

eess.SY↗

arXiv2022

Rate-Distortion Theory for Strategic Semantic Communication

This paper analyzes the fundamental limit of the strategic semantic communication problem in which a transmitter obtains a limited number of indirect observation of an intrinsic semantic information source and can then influence the receiver's decoding by sending a limited number of messages to an imperfect channel. The transmitter and the receiver can have different distortion measures and can make rational decision about their encoding and decoding strategies, respectively. The decoder can also have some side information (e.g., background knowledge and/or information obtained from previous communications) about the semantic source to assist its interpretation of the semantic information. We focus particularly on the case that the transmitter can commit to an encoding strategy and study the impact of the strategic decision making on the rate distortion of semantic communication. Three equilibrium solutions including the strong Stackelberg equilibrium, weak Stackelberg equilibrium, as well as Nash equilibrium have been studied and compared. The optimal encoding and decoding strategy profiles under various equilibrium solutions have been derived. We prove that committing to an encoding strategy cannot always bring benefit to the encoder. We therefore propose a feasible condition under which committing to an encoding strategy can always reduce the distortion performance of semantic communication.

cs.IT↗

arXiv2022

The H-property of Line Graphons

We explore in this paper sufficient conditions for the $H$-property to hold, with a particular focus on the so-called line graphons. A graphon is a symmetric, measurable function from the unit square $[0,1]^2$ to the closed interval $[0,1]$. Graphons can be used to sample random graphs, and a graphon is said to have the $H$-property if graphs on $n$ nodes sampled from it admit a node-cover by disjoint cycles -- such a cover is called a Hamiltonian decomposition -- almost surely as $n \to \infty$. A step-graphon is a graphon which is piecewise constant over rectangles in the domain. To a step-graphon, we assign two objects: its concentration vector, encoding the areas of the rectangles, and its skeleton-graph, describing their supports. These two objects were used in our earlier work [3] to establish necessary conditions for a step-graphon to have the $H$-property. In this paper, we prove that these conditions are essentially also sufficient for the class of line-graphons, i.e., the step-graphons whose skeleton graphs are line graphs with a self-loop at an ending node. We also investigate borderline cases where neither the necessary nor the sufficient conditions are met.

math.OC↗

arXiv2021

Decentralized Multi-Task Stochastic Optimization With Compressed Communications

We consider a multi-agent network where each node has a stochastic (local) cost function that depends on the decision variable of that node and a random variable, and further the decision variables of neighboring nodes are pairwise constrained. There is an aggregate objective function for the network, composed additively of the expected values of the local cost functions at the nodes, and the overall goal of the network is to obtain the minimizing solution to this aggregate objective function subject to all the pairwise constraints. This is to be achieved at the node level using decentralized information and local computation, with exchanges of only compressed information allowed by neighboring nodes. The paper develops algorithms and obtains performance bounds for two different models of local information availability at the nodes: (i) sample feedback, where each node has direct access to samples of the local random variable to evaluate its local cost, and (ii) bandit feedback, where samples of the random variables are not available, but only the values of the local cost functions at two random points close to the decision are available to each node. For both models, with compressed communication between neighbors, we have developed decentralized saddle-point algorithms that deliver performances no different (in order sense) from those without communication compression; specifically, we show that deviation from the global minimum value and violations of the constraints are upper-bounded by $\mathcal{O}(T^{-\frac{1}{2}})$ and $\mathcal{O}(T^{-\frac{1}{4}})$, respectively, where $T$ is the number of iterations. Numerical examples provided in the paper corroborate these bounds and demonstrate the communication efficiency of the proposed method.

math.OC↗

arXiv2021

On the H-property for step-graphons and edge polytopes

Graphons $W$ can be used as stochastic models to sample graphs $G_n$ on $n$ nodes for $n$ arbitrarily large. A graphon $W$ is said to have the $H$-property if $G_n$ admits a decomposition into disjoint cycles with probability one as $n$ goes to infinity. Such a decomposition is known as a Hamiltonian decomposition. In this paper, we provide necessary conditions for the $H$-property to hold. The proof builds upon a hereby established connection between the so-called edge polytope of a finite undirected graph associated with $W$ and the $H$-property. Building on its properties, we provide a purely geometric solution to a random graph problem. More precisely, we assign two natural objects to $W$, which we term concentration vector and skeleton graph, denoted by $x^*$ and $S$ respectively. We then establish two necessary conditions for the $H$-property to hold: (1) the edge-polytope of $S$, denoted by $\mathcal{X}(S)$, is of full rank, and (2) $x^* \in \mathcal{X}(S)$.

math.OC↗

arXiv2021

Decentralized Q-Learning in Zero-sum Markov Games

We study multi-agent reinforcement learning (MARL) in infinite-horizon discounted zero-sum Markov games. We focus on the practical but challenging setting of decentralized MARL, where agents make decisions without coordination by a centralized controller, but only based on their own payoffs and local actions executed. The agents need not observe the opponent's actions or payoffs, possibly being even oblivious to the presence of the opponent, nor be aware of the zero-sum structure of the underlying game, a setting also referred to as radically uncoupled in the literature of learning in games. In this paper, we develop a radically uncoupled Q-learning dynamics that is both rational and convergent: the learning dynamics converges to the best response to the opponent's strategy when the opponent follows an asymptotically stationary strategy; when both agents adopt the learning dynamics, they converge to the Nash equilibrium of the game. The key challenge in this decentralized setting is the non-stationarity of the environment from an agent's perspective, since both her own payoffs and the system evolution depend on the actions of other agents, and each agent adapts her policies simultaneously and independently. To address this issue, we develop a two-timescale learning dynamics where each agent updates her local Q-function and value function estimates concurrently, with the latter happening at a slower timescale.

cs.GT↗

arXiv2021

The Confluence of Networks, Games and Learning

Recent years have witnessed significant advances in technologies and services in modern network applications, including smart grid management, wireless communication, cybersecurity as well as multi-agent autonomous systems. Considering the heterogeneous nature of networked entities, emerging network applications call for game-theoretic models and learning-based approaches in order to create distributed network intelligence that responds to uncertainties and disruptions in a dynamic or an adversarial environment. This paper articulates the confluence of networks, games and learning, which establishes a theoretical underpinning for understanding multi-agent decision-making over networks. We provide an selective overview of game-theoretic learning algorithms within the framework of stochastic approximation theory, and associated applications in some representative contexts of modern network systems, such as the next generation wireless communication networks, the smart grid and distributed machine learning. In addition to existing research works on game-theoretic learning over networks, we highlight several new angles and research endeavors on learning in games that are related to recent developments in artificial intelligence. Some of the new angles extrapolate from our own research interests. The overall objective of the paper is to provide the reader a clear picture of the strengths and challenges of adopting game-theoretic learning methods within the context of network systems, and further to identify fruitful future research directions on both theoretical and applied studies.

cs.MA↗

arXiv2021

Infinite-horizon Risk-constrained Linear Quadratic Regulator with Average Cost

The behaviour of a stochastic dynamical system may be largely influenced by those low-probability, yet extreme events. To address such occurrences, this paper proposes an infinite-horizon risk-constrained Linear Quadratic Regulator (LQR) framework with time-average cost. In addition to the standard LQR objective, the average one-stage predictive variance of the state penalty is constrained to lie within a user-specified level. By leveraging the duality, its optimal solution is first shown to be stationary and affine in the state, i.e., $u(x,\lambda^*) = -K(\lambda^*)x + l(\lambda^*)$, where $\lambda^*$ is an optimal multiplier, used to address the risk constraint. Then, we establish the stability of the resulting closed-loop system. Furthermore, we propose a primal-dual method with sublinear convergence rate to find an optimal policy $u(x,\lambda^*)$. Finally, a numerical example is provided to demonstrate the effectiveness of the proposed framework and the primal-dual method.

math.OC↗

arXiv2020

Fixed-Time Nash Equilibrium Seeking in Non-Cooperative Games

We introduce a novel class of Nash equilibrium seeking dynamics for non-cooperative games with a finite number of players, where the convergence to the Nash equilibrium is bounded by a KL function with a settling time that can be upper bounded by a positive constant that is independent of the initial conditions of the players, and which can be prescribed a priori by the system designer. The dynamics are model-free, in the sense that the mathematical forms of the cost functions of the players are unknown. Instead, in order to update its own action, each player needs to have access only to real-time evaluations of its own cost, as well as to auxiliary states of neighboring players characterized by a communication graph. Stability and convergence properties are established for both potential games and strongly monotone games. Numerical examples are presented to illustrate our theoretical results.

math.OC↗