Gehui Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Gehui Xu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Guanpu Chen
Southeast University
10 shared publications - Yiguang Hong
Department of Control Science and Engineering, Tongji University, Shanghai, China
8 shared publications - Hongsheng Qi
State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China
4 shared publications - Karl Henrik Johansson
KTH Royal Institute of Technology
4 shared publications - Thomas Parisini
Imperial College London
4 shared publications - Baris Fidan
Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON, Canada
3 shared publications
Latest Publications
- 18 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 71 (5) , 3357-3364
Inverse Learning of Black-Box Aggregator for Robust Nash Equilibrium
In this article, we study the robustness of the Nash equilibrium (NE) in aggregative games with coupling constraints. When the constraint parameters are uncertain, the associated NE might be perturbed. It is essential to find a robust NE satisfying all possible constraints affected by the uncertain parameters. Although some methods have been developed for robust NE, these results rely on complete information about the game. We instead consider a scenario when only the uncertain parameters and associated perturbed NE are available, but the players’ weights in the aggregator are unknown. With the uncertain parameters and perturbed NE constituting data, we propose data-based optimization to inversely learn players’ weights in the black-box aggregator. We then use the learned weights in a transformed augmented problem without uncertainty and derive the first-order conditions for computing the robust NE. Furthermore, we characterize the generalization guarantee of the proposed learning approach in terms of violation probability.
- 18 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 71 (5) , 3357-3364
Inverse Learning of Black-Box Aggregator for Robust Nash Equilibrium
In this article, we study the robustness of the Nash equilibrium (NE) in aggregative games with coupling constraints. When the constraint parameters are uncertain, the associated NE might be perturbed. It is essential to find a robust NE satisfying all possible constraints affected by the uncertain parameters. Although some methods have been developed for robust NE, these results rely on complete information about the game. We instead consider a scenario when only the uncertain parameters and associated perturbed NE are available, but the players’ weights in the aggregator are unknown. With the uncertain parameters and perturbed NE constituting data, we propose data-based optimization to inversely learn players’ weights in the black-box aggregator. We then use the learned weights in a transformed augmented problem without uncertainty and derive the first-order conditions for computing the robust NE. Furthermore, we characterize the generalization guarantee of the proposed learning approach in terms of violation probability.
- 19 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (12) , 10797-10813
Approaching the Global Nash Equilibrium of Non-Convex Multi-Player Games
Many machine learning problems can be formulated as non-convex multi-player games. Due to non-convexity, it is challenging to obtain the existence condition of the global Nash equilibrium (NE) and design theoretically guaranteed algorithms. This paper studies a class of non-convex multi-player games, where players’ payoff functions consist of canonical functions and quadratic operators. We leverage conjugate properties to transform the complementary problem into a variational inequality (VI) problem using a continuous pseudo-gradient mapping. We prove the existence condition of the global NE as the solution to the VI problem satisfies a duality relation. We then design an ordinary differential equation to approach the global NE with an exponential convergence rate. For practical implementation, we derive a discretized algorithm and apply it to two scenarios: multi-player games with generalized monotonicity and multi-player potential games. In the two settings, step sizes are required to be$\mathcal {O}(1/k)$ and$\mathcal {O}(1/\sqrt{k})$ to yield the convergence rates of$\mathcal {O}(1/ k)$ and$\mathcal {O}(1/\sqrt{k})$ , respectively. Extensive experiments on robust neural network training and sensor network localization validate our theory. Our code is available at https://github.com/GuanpuChen/Global-NE .- 19 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (12) , 10797-10813
Approaching the Global Nash Equilibrium of Non-Convex Multi-Player Games
Many machine learning problems can be formulated as non-convex multi-player games. Due to non-convexity, it is challenging to obtain the existence condition of the global Nash equilibrium (NE) and design theoretically guaranteed algorithms. This paper studies a class of non-convex multi-player games, where players’ payoff functions consist of canonical functions and quadratic operators. We leverage conjugate properties to transform the complementary problem into a variational inequality (VI) problem using a continuous pseudo-gradient mapping. We prove the existence condition of the global NE as the solution to the VI problem satisfies a duality relation. We then design an ordinary differential equation to approach the global NE with an exponential convergence rate. For practical implementation, we derive a discretized algorithm and apply it to two scenarios: multi-player games with generalized monotonicity and multi-player potential games. In the two settings, step sizes are required to be$\mathcal {O}(1/k)$ and$\mathcal {O}(1/\sqrt{k})$ to yield the convergence rates of$\mathcal {O}(1/ k)$ and$\mathcal {O}(1/\sqrt{k})$ , respectively. Extensive experiments on robust neural network training and sensor network localization validate our theory. Our code is available at https://github.com/GuanpuChen/Global-NE .- 16 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 11 (5) , 5099-5113
Enable Microgrid Energy Management: A Graph Based Aggregative Game Approach
With the rising adoption of distributed and intermittent renewable energy sources, microgrids have emerged as a promising solution to the resulting challenges. Specifically, microgrids could rely on energy storage systems (ESSs) to balance power generation and varying loads. However, an increased number of ESSs, if not well coordinated, can lead to an increase in system operation costs. To overcome this issue, we adopt a graph-based aggregative game to regulate the charging and discharging strategies of multiple ESSs. We show the existence and uniqueness of the Nash equilibrium (NE) and propose the corresponding Graph-based Aggregative Charging Tracking (GACT) distributed algorithm to compute NE with a linear convergence rate. Our algorithm leverages existing communication resources efficiently and protects the private charging information of ESSs. Numerical experiments demonstrate the effectiveness of our proposed algorithm.
- 16 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 11 (5) , 5099-5113
Enable Microgrid Energy Management: A Graph Based Aggregative Game Approach
With the rising adoption of distributed and intermittent renewable energy sources, microgrids have emerged as a promising solution to the resulting challenges. Specifically, microgrids could rely on energy storage systems (ESSs) to balance power generation and varying loads. However, an increased number of ESSs, if not well coordinated, can lead to an increase in system operation costs. To overcome this issue, we adopt a graph-based aggregative game to regulate the charging and discharging strategies of multiple ESSs. We show the existence and uniqueness of the Nash equilibrium (NE) and propose the corresponding Graph-based Aggregative Charging Tracking (GACT) distributed algorithm to compute NE with a linear convergence rate. Our algorithm leverages existing communication resources efficiently and protects the private charging information of ESSs. Numerical experiments demonstrate the effectiveness of our proposed algorithm.
- Open Access
A Multi-Player Potential Game Approach for Sensor Network Localization with Noisy Measurements
Sensor network localization (SNL) is a challenging problem due to its inherent non-convexity and the effects of noise in inter-node ranging measurements and anchor node position. We formulate a non-convex SNL problem as a multi-player non-convex potential game and investigate the existence and uniqueness of a Nash equilibrium (NE) in both the ideal setting without measurement noise and the practical setting with measurement noise. We first show that the NE exists and is unique in the noiseless case, and corresponds to the precise network localization. Then, we study the SNL for the case with errors affecting the anchor node position and the inter-node distance measurements. Specifically, we establish that in case these errors are sufficiently small, the NE exists and is unique. It is shown that the NE is an approximate solution to the SNL problem, and that the position errors can be quantified accordingly. Based on these findings, we apply the results to case studies involving only inter-node distance measurement errors and only anchor position information inaccuracies.
Open AccessA Multi-Player Potential Game Approach for Sensor Network Localization with Noisy Measurements
Sensor network localization (SNL) is a challenging problem due to its inherent non-convexity and the effects of noise in inter-node ranging measurements and anchor node position. We formulate a non-convex SNL problem as a multi-player non-convex potential game and investigate the existence and uniqueness of a Nash equilibrium (NE) in both the ideal setting without measurement noise and the practical setting with measurement noise. We first show that the NE exists and is unique in the noiseless case, and corresponds to the precise network localization. Then, we study the SNL for the case with errors affecting the anchor node position and the inter-node distance measurements. Specifically, we establish that in case these errors are sufficiently small, the NE exists and is unique. It is shown that the NE is an approximate solution to the SNL problem, and that the position errors can be quantified accordingly. Based on these findings, we apply the results to case studies involving only inter-node distance measurement errors and only anchor position information inaccuracies.
- 6 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 5330-5344
Consistency of Stackelberg and Nash Equilibria in Three-Player Leader-Follower Games
There has been significant recent interest in a class of three-player leader-follower game models in many important cybersecurity scenarios. In such a tri-level hierarchical structure, a defender usually serves as a leader, dominating the decision process by the Stackelberg equilibrium (SE) strategy. However, such a leader-follower scheme may not always work, and the Nash equilibrium (NE) strategy may provide an alternative choice. Thus, we need to reveal the consistency between SE and NE in the three-player model to help the leader evaluate its strategy impact and avoid a choice dilemma. To this end, we first provide a necessary and sufficient condition such that each SE is an NE, which not only provides access to seek a satisfactory SE but also makes a criterion for an obtained SE. Then, we apply the results for case studies with a unique SE or with at least one SE being an NE. Moreover, when the consistency condition falls short, we give an upper bound of the deviation between SE and NE to help the leader tolerably adopt an SE strategy. Finally, we apply our consistency analysis to practical scenarios, including secure wireless transmission and advanced persistent threat defense.
- 6 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 5330-5344
Consistency of Stackelberg and Nash Equilibria in Three-Player Leader-Follower Games
There has been significant recent interest in a class of three-player leader-follower game models in many important cybersecurity scenarios. In such a tri-level hierarchical structure, a defender usually serves as a leader, dominating the decision process by the Stackelberg equilibrium (SE) strategy. However, such a leader-follower scheme may not always work, and the Nash equilibrium (NE) strategy may provide an alternative choice. Thus, we need to reveal the consistency between SE and NE in the three-player model to help the leader evaluate its strategy impact and avoid a choice dilemma. To this end, we first provide a necessary and sufficient condition such that each SE is an NE, which not only provides access to seek a satisfactory SE but also makes a criterion for an obtained SE. Then, we apply the results for case studies with a unique SE or with at least one SE being an NE. Moreover, when the consistency condition falls short, we give an upper bound of the deviation between SE and NE to help the leader tolerably adopt an SE strategy. Finally, we apply our consistency analysis to practical scenarios, including secure wireless transmission and advanced persistent threat defense.
- Open Access
Non-convex potential games for finding global solutions to sensor network localization
Sensor network localization (SNL) problems require determining the physical coordinates of all sensors in a network. This process relies on the global coordinates of anchors and the available measurements between non-anchor and anchor nodes. Attributed to the intrinsic non-convexity, obtaining a globally optimal solution to SNL is challenging, as well as implementing corresponding algorithms. In this paper, we formulate a non-convex multi-player potential game for a generic SNL problem to investigate the identification condition of the global Nash equilibrium (NE) therein, where the global NE represents the global solution of SNL. We employ canonical duality theory to transform the non-convex game into a complementary dual problem. Then we develop a conjugation-based algorithm to compute the stationary points of the complementary dual problem. On this basis, we show an identification condition of the global NE: the stationary point of the proposed algorithm satisfies a duality relation. Finally, simulation results are provided to validate the effectiveness of the theoretical results.
Open AccessNon-convex potential games for finding global solutions to sensor network localization
Sensor network localization (SNL) problems require determining the physical coordinates of all sensors in a network. This process relies on the global coordinates of anchors and the available measurements between non-anchor and anchor nodes. Attributed to the intrinsic non-convexity, obtaining a globally optimal solution to SNL is challenging, as well as implementing corresponding algorithms. In this paper, we formulate a non-convex multi-player potential game for a generic SNL problem to investigate the identification condition of the global Nash equilibrium (NE) therein, where the global NE represents the global solution of SNL. We employ canonical duality theory to transform the non-convex game into a complementary dual problem. Then we develop a conjugation-based algorithm to compute the stationary points of the complementary dual problem. On this basis, we show an identification condition of the global NE: the stationary point of the proposed algorithm satisfies a duality relation. Finally, simulation results are provided to validate the effectiveness of the theoretical results.
- Open Access
Global solution to sensor network localization: A non-convex potential game approach and its distributed implementation
Consider a sensor network consisting of both anchor and non-anchor nodes. We address the following sensor network localization (SNL) problem: given the physical locations of anchor nodes and relative measurements among all nodes, determine the locations of all non-anchor nodes. The solution to the SNL problem is challenging due to its inherent non-convexity. In this paper, the problem takes on the form of a multi-player non-convex potential game in which canonical duality theory is used to define a complementary dual potential function. After showing the Nash equilibrium (NE) correspondent to the SNL solution, we provide a necessary and sufficient condition for a stationary point to coincide with the NE. An algorithm is proposed to reach the NE and shown to have convergence rate $\mathcal{O}(1/\sqrt{k})$. With the aim of reducing the information exchange within a network, a distributed algorithm for NE seeking is implemented and its global convergence analysis is provided. Extensive simulations show the validity and effectiveness of the proposed approach to solve the SNL problem.Open AccessGlobal solution to sensor network localization: A non-convex potential game approach and its distributed implementation
Consider a sensor network consisting of both anchor and non-anchor nodes. We address the following sensor network localization (SNL) problem: given the physical locations of anchor nodes and relative measurements among all nodes, determine the locations of all non-anchor nodes. The solution to the SNL problem is challenging due to its inherent non-convexity. In this paper, the problem takes on the form of a multi-player non-convex potential game in which canonical duality theory is used to define a complementary dual potential function. After showing the Nash equilibrium (NE) correspondent to the SNL solution, we provide a necessary and sufficient condition for a stationary point to coincide with the NE. An algorithm is proposed to reach the NE and shown to have convergence rate $\mathcal{O}(1/\sqrt{k})$. With the aim of reducing the information exchange within a network, a distributed algorithm for NE seeking is implemented and its global convergence analysis is provided. Extensive simulations show the validity and effectiveness of the proposed approach to solve the SNL problem. - 19 April 2023
- Published by Springer Nature in Journal of Systems Science and Complexity
- Vol. 36 (2) , 480-499
Algorithm Design and Approximation Analysis on Distributed Robust Game
- 19 April 2023
- Published by Springer Nature in Journal of Systems Science and Complexity
- Vol. 36 (2) , 480-499
Algorithm Design and Approximation Analysis on Distributed Robust Game
- 14 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 68 (11) , 6921-6928
Distributed Mirror Descent Algorithm With Bregman Damping for Nonsmooth Constrained Optimization
To efficiently solve the nonsmooth distributed optimization with both local constraints and coupled constraints, we propose a distributed continuous-time algorithm based on the mirror descent (MD) method. In this article, we introduce the Bregman damping into distributed MD-based dynamics, which not only successfully applies the MD idea to the distributed primal-dual framework, but also ensures the boundedness of all variables and the convergence of the entire dynamics. Our approach generalizes the classic distributed projection-based dynamics, and establishes a connection between MD methods and distributed Euclidean-projected approaches. Also, we prove the convergence of the proposed distributed dynamics with an $ \mathcal {O}(1/t)$ rate. For practical implementation, we further give a discrete-time algorithm based on the proposed dynamics with an $ \mathcal {O}(1/\sqrt{k})$ convergence rate.
- 14 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 68 (11) , 6921-6928
Distributed Mirror Descent Algorithm With Bregman Damping for Nonsmooth Constrained Optimization
To efficiently solve the nonsmooth distributed optimization with both local constraints and coupled constraints, we propose a distributed continuous-time algorithm based on the mirror descent (MD) method. In this article, we introduce the Bregman damping into distributed MD-based dynamics, which not only successfully applies the MD idea to the distributed primal-dual framework, but also ensures the boundedness of all variables and the convergence of the entire dynamics. Our approach generalizes the classic distributed projection-based dynamics, and establishes a connection between MD methods and distributed Euclidean-projected approaches. Also, we prove the convergence of the proposed distributed dynamics with an $ \mathcal {O}(1/t)$ rate. For practical implementation, we further give a discrete-time algorithm based on the proposed dynamics with an $ \mathcal {O}(1/\sqrt{k})$ convergence rate.
- Open Access
Global Nash Equilibrium in Non-convex Multi-player Game: Theory and Algorithms
Wide machine learning tasks can be formulated as non-convex multi-player games, where Nash equilibrium (NE) is an acceptable solution to all players, since no one can benefit from changing its strategy unilaterally. Attributed to the non-convexity, obtaining the existence condition of global NE is challenging, let alone designing theoretically guaranteed realization algorithms. This paper takes conjugate transformation to the formulation of non-convex multi-player games, and casts the complementary problem into a variational inequality (VI) problem with a continuous pseudo-gradient mapping. We then prove the existence condition of global NE: the solution to the VI problem satisfies a duality relation. Based on this VI formulation, we design a conjugate-based ordinary differential equation (ODE) to approach global NE, which is proved to have an exponential convergence rate. To make the dynamics more implementable, we further derive a discretized algorithm. We apply our algorithm to two typical scenarios: multi-player generalized monotone game and multi-player potential game. In the two settings, we prove that the step-size setting is required to be $\mathcal{O}(1/k)$ and $\mathcal{O}(1/\sqrt k)$ to yield the convergence rates of $\mathcal{O}(1/ k)$ and $\mathcal{O}(1/\sqrt k)$, respectively. Extensive experiments in robust neural network training and sensor localization are in full agreement with our theory.Open AccessGlobal Nash Equilibrium in Non-convex Multi-player Game: Theory and Algorithms
Wide machine learning tasks can be formulated as non-convex multi-player games, where Nash equilibrium (NE) is an acceptable solution to all players, since no one can benefit from changing its strategy unilaterally. Attributed to the non-convexity, obtaining the existence condition of global NE is challenging, let alone designing theoretically guaranteed realization algorithms. This paper takes conjugate transformation to the formulation of non-convex multi-player games, and casts the complementary problem into a variational inequality (VI) problem with a continuous pseudo-gradient mapping. We then prove the existence condition of global NE: the solution to the VI problem satisfies a duality relation. Based on this VI formulation, we design a conjugate-based ordinary differential equation (ODE) to approach global NE, which is proved to have an exponential convergence rate. To make the dynamics more implementable, we further derive a discretized algorithm. We apply our algorithm to two typical scenarios: multi-player generalized monotone game and multi-player potential game. In the two settings, we prove that the step-size setting is required to be $\mathcal{O}(1/k)$ and $\mathcal{O}(1/\sqrt k)$ to yield the convergence rates of $\mathcal{O}(1/ k)$ and $\mathcal{O}(1/\sqrt k)$, respectively. Extensive experiments in robust neural network training and sensor localization are in full agreement with our theory.