no code implementations • 17 Apr 2024 • Alexander Davydov, Francesco Bullo
Contraction theory is a mathematical framework for studying the convergence, robustness, and modularity properties of dynamical systems and algorithms.
no code implementations • 12 Feb 2024 • Sean Jaffe, Alexander Davydov, Deniz Lapsekili, Ambuj Singh, Francesco Bullo
Global stability and robustness guarantees in learned dynamical systems are essential to ensure well-behavedness of the systems in the face of uncertainty.
no code implementations • 12 Dec 2023 • Sean Jaffe, Ambuj K. Singh, Francesco Bullo
We also introduce a variant, IDKM with Jacobian-Free-Backpropagation (IDKM-JFB), for which the time complexity of the gradient calculation is independent of $t$ as well.
no code implementations • 7 Nov 2023 • Veronica Centorrino, Anand Gokhale, Alexander Davydov, Giovanni Russo, Francesco Bullo
Our analysis leverages contraction theory to characterize the behavior of a family of firing-rate competitive networks for sparse reconstruction with and without non-negativity constraints.
no code implementations • 4 Nov 2023 • Rui Yan, Xiaoming Duan, Rui Zou, Xin He, Zongying Shi, Francesco Bullo
We propose a cooperative strategy for the pursuers based on subgames for multiple pursuers against one evader and optimal task allocation.
no code implementations • 12 Oct 2023 • Liliaokeawawa Cothren, Francesco Bullo, Emiliano Dall'Anese
In this paper, we provide a novel contraction-theoretic approach to analyze two-time scale systems.
no code implementations • 28 Aug 2023 • Yohan John, Gilberto Diaz-Garcia, Xiaoming Duan, Jason R. Marden, Francesco Bullo
Stochastic patrol routing is known to be advantageous in adversarial settings; however, the optimal choice of stochastic routing strategy is dependent on a model of the adversary.
no code implementations • 2 May 2023 • Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen
In this work, a data-based formulation for computing the steady-state Kalman gain is proposed based on semi-definite programming (SDP) using some noise-free input-state-output data.
no code implementations • 17 Dec 2022 • Wenjun Mei, Julien M. Hendrickx, Ge Chen, Francesco Bullo, Florian Dörfler
Moreover, we prove a necessary and sufficient graph-theoretic condition for the almost-sure convergence to consensus, as well as a sufficient graph-theoretic condition for almost-sure persistent dissensus.
no code implementations • 8 Aug 2022 • Saber Jafarpour, Alexander Davydov, Matthew Abate, Francesco Bullo, Samuel Coogan
Third, we use the upper bounds of the Lipschitz constants and the upper bounds of the tight inclusion functions to design two algorithms for the training and robustness verification of implicit neural networks.
no code implementations • 18 Jul 2022 • Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen
Self-triggered control, a well-documented technique for reducing the communication overhead while ensuring desired system performance, is gaining increasing popularity.
1 code implementation • 1 Apr 2022 • Alexander Davydov, Saber Jafarpour, Matthew Abate, Francesco Bullo, Samuel Coogan
We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs).
no code implementations • 10 Jan 2022 • Marco Coraggio, Saber Jafarpour, Francesco Bullo, Mario di Bernardo
Given a flow network with variable suppliers and fixed consumers, the minimax flow problem consists in minimizing the maximum flow between nodes, subject to flow conservation and capacity constraints.
1 code implementation • 8 Jan 2022 • Wei Ye, Francesco Bullo, Noah Friedkin, Ambuj K Singh
AI and humans bring complementary skills to group deliberations.
no code implementations • 10 Dec 2021 • Saber Jafarpour, Matthew Abate, Alexander Davydov, Francesco Bullo, Samuel Coogan
First, given an implicit neural network, we introduce a related embedded network and show that, given an $\ell_\infty$-norm box constraint on the input, the embedded network provides an $\ell_\infty$-norm box overapproximation for the output of the given network.
no code implementations • 25 Oct 2021 • Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen
Finally, a numerical example is given to validate the effectiveness of the proposed control method.
1 code implementation • NeurIPS 2021 • Saber Jafarpour, Alexander Davydov, Anton V. Proskurnikov, Francesco Bullo
Additionally, we design a training problem with the well-posedness condition and the average iteration as constraints and, to achieve robust models, with the input-output Lipschitz constant as a regularizer.
no code implementations • 18 May 2021 • Pedro Cisneros-Velarde, Francesco Bullo
Much recent interest has focused on the design of optimization algorithms from the discretization of an associated optimization flow, i. e., a system of differential equations (ODEs) whose trajectories solve an associated optimization problem.
no code implementations • 22 Mar 2021 • Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen
When both input and output channels are subject to DoS attacks and quantization, the proposed structure is shown able to decouple the encoding schemes for input, output, and estimated output signals.
no code implementations • ICLR 2021 • Arlei Lopes da Silva, Furkan Kocayusufoglu, Saber Jafarpour, Francesco Bullo, Ananthram Swami, Ambuj Singh
The flow estimation problem consists of predicting missing edge flows in a network (e. g., traffic, power and water) based on partial observations.
no code implementations • 15 Dec 2020 • Pedro Cisneros-Velarde, Francesco Bullo
Consider a multi-agent system whereby each agent has an initial probability measure.
1 code implementation • 13 Nov 2020 • Omid Askarisichani, Elizabeth Y. Huang, Kekoa S. Sato, Noah E. Friedkin, Francesco Bullo, Ambuj K. Singh
Lastly, we propose a novel approach using deep neural networks on a pre-trained text embedding model for predicting the influence of individuals.
no code implementations • 17 Jun 2020 • Rui Yan, Xiaoming Duan, Zongying Shi, Yisheng Zhong, Jason R. Marden, Francesco Bullo
With this knowledge we propose a class of perturbed SBRD with the following property: only policies with maximum metric are observed with nonzero probability for a broad class of stochastic games with finite memory.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 16 May 2020 • Kevin D. Smith, Saber Jafarpour, Ananthram Swami, Francesco Bullo
Many tasks regarding the monitoring, management, and design of communication networks rely on knowledge of the routing topology.
no code implementations • 27 Mar 2020 • Pedro Cisneros-Velarde, Saber Jafarpour, Francesco Bullo
In this note, we provide an overarching analysis of primal-dual dynamics associated to linear equality-constrained optimization problems using contraction analysis.