15 May 2018 in IEEE Transactions on Automatic Control
We investigate the vulnerabilities of consensus-based distributed optimization protocols to nodes that deviate from the prescribed update rule (e.g., due to failures or adversarial attacks). We first characterize certain fundamental limitations on the performance of any distributed optimization algorithm in the presence of adversaries. We then propose a secure distributed optimization algorithm that guarantees that the non-adversarial nodes converge to the convex hull of the minimizers of their local functions under certain conditions on the graph topology, regardless of the actions of a certain number of adversarial nodes. In particular, we provide sufficient conditions on the graph topology to tolerate a bounded number of adversaries in the neighborhood of every non-adversarial node, and necessary and sufficient conditions to tolerate a globally bounded number of adversaries. For situations where there are up to F adversaries in the neighborhood of every node, we use the concept of maximal F-local sets of graphs to provide lower bounds on the distance-to-optimality of achievable solutions under any algorithm.
17 August 2017 in IEEE Transactions on Control of Network Systems
We consider a class of distributed submodular maximization problems in which each agent must choose a single strategy from its strategy set. The global objective is to maximize a submodular function of the strategies chosen by each agent. When choosing a strategy, each agent has access to only a limited number of other agents' choices. For each of its strategies, an agent can evaluate its marginal contribution to the global objective given its information. The main objective is to investigate how this limitation of information about the strategies chosen by other agents affects the performance when agents make choices according to a local greedy algorithm. In particular, we provide lower bounds on the performance of greedy algorithms for submodular maximization, which depend on the clique number of a graph that captures the information structure. We also characterize graph-theoretic upper bounds in terms of the chromatic number of the graph. Finally, we demonstrate how certain graph properties limit the performance of the greedy algorithm. Simulations on several common models for random networks demonstrate our results.
12 July 2022 in IEEE Transactions on Automatic Control
In this paper we show that deep residual neural networks have the power of universal approximation by using, in an essential manner, the observation that these networks can be modeled as nonlinear control systems. We first study the problem of using a deep residual neural network to exactly memorize training data by formulating it as a controllability problem for an ensemble control system. Using techniques from geometric control theory, we identify a class of activation functions that allow us to ensure controllability on an open and dense submanifold of sample points. Using this result, and resorting to the notion of monotonicity, we establish that any continuous function can be approximated on a compact set to arbitrary accuracy, with respect to the uniform norm, by this class of neural networks. Moreover, we provide optimal bounds on the number of required neurons.
26 February 2021 in IEEE Transactions on Automatic Control
This article studies the event-triggered control problem of general nonlinear systems with time delay. A novel event-triggering scheme is presented with two tunable design parameters, based on a Lyapunov functional result for the input-to-state stability of time-delay systems. The proposed event-triggered control algorithm guarantees the resulting closed-loop systems to be globally asymptotically stable, uniformly bounded, and/or globally attractive for different choices of these parameters. Sufficient conditions on the parameters are derived to exclude Zeno behavior. Two illustrative examples are studied to demonstrate our theoretical results.
27 July 2018 in IEEE Transactions on Automatic Control
We consider a distributed online optimization problem where, at each time, a group of agents choose their individual states, after which an individual cost function is revealed to each of them. The whole network then faces a regret according to the cumulative sum of costs incurred by the agents' chosen states, and each agent faces an individual regret according to the cumulative sum of costs incurred by the agent's state estimation, perceived as the whole network's chosen state. In order to tackle the minimization of the individual regret using only local information, we assume that the group of agents communicate over a fixed undirected connected graph. We then propose an online version of the Alternating Direction Method of Multipliers (ADMM) algorithm, distributed over the communication graph, that allows each agent to drive its individual average regret over time to zero.
17 July 2019 in IEEE Transactions on Automatic Control
In this paper, we study the problem of achieving average consensus over a random time-varying sequence of directed graphs by extending the class of so-called push-sum algorithms to such random scenarios. Provided that an ergodicity notion, which we term the directed infinite flow property, holds and the auxiliary states of agents are uniformly bounded away from zero infinitely often, we prove the almost sure convergence of the evolutions of this class of algorithms to the average of initial states. Moreover, for a random sequence of graphs generated using a so-called time-varying B-irreducible probability matrix, we establish convergence rates for the proposed push-sum algorithm.