arXiv subjects

Matthew T. Hale

Publications and source records attributed to Matthew T. Hale.

16 recordsLinked to original sources

arXiv2026

Distributed Nonconvex Optimization with Exponential Convergence Rate via Hybrid Systems Methods

We present a hybrid systems framework for distributed multi-agent optimization in which agents execute computations in continuous time and communicate in discrete time. The optimization algorithm is analogous to a continuous-time form of parallelized coordinate descent. Agents implement an update-and-hold strategy in which gradients are computed at communication times and held constant during flows between communications. The completeness of solutions under these hybrid dynamics is established. Then, we prove that this system is globally exponentially stable to a minimizer of a possibly nonconvex, smooth objective function that satisfies the Polyak-Lojasiewicz (PL) condition. Simulation results are presented for three different applications and illustrate the convergence rates and the impact of initial conditions upon convergence.

math.OC↗

arXiv2026

Autonomous Satellite Rendezvous via Hybrid Feedback Optimization

As satellites have proliferated, interest has increased in autonomous rendezvous, proximity operations, and docking (ARPOD). A fundamental challenge in these tasks is the uncertainties when operating in space, e.g., in measurements of satellites' states, which can make future states difficult to predict. Another challenge is that satellites' onboard processors are typically much slower than their terrestrial counterparts. Therefore, to address these challenges we propose to solve an ARPOD problem with feedback optimization, which computes inputs to a system by measuring its outputs, feeding them into an optimization algorithm in the loop, and computing some number of iterations towards an optimal input. We focus on satellite rendezvous, and satellites' dynamics are modeled using the continuous-time Clohessy-Wiltshire equations, which are marginally stable. We develop an asymptotically stabilizing controller for them, and we use discrete-time gradient descent in the loop to compute inputs to them. Then, we analyze the hybrid feedback optimization system formed by the stabilized Clohessy-Wiltshire equations with gradient descent in the loop. We show that this model is well-posed and that maximal solutions are both complete and non-Zeno. Then, we show that solutions converge exponentially fast to a ball around a rendezvous point, and we bound the radius of that ball in terms of system parameters. Simulations show that this approach provides up to a 98.4\% reduction in the magnitude of disturbances across a range of simulations, which illustrates the viability of hybrid feedback optimization for autonomous satellite rendezvous.

eess.SY↗

arXiv2025

Technical Report: Pose Graph Optimization over Planar Unit Dual Quaternions: Improved Accuracy with Provably Convergent Riemannian Optimization

It is common in pose graph optimization (PGO) algorithms to assume that noise in the translations and rotations of relative pose measurements is uncorrelated. However, existing work shows that in practice these measurements can be highly correlated, which leads to degradation in the accuracy of PGO solutions that rely on this assumption. Therefore, in this paper we develop a novel algorithm derived from a realistic, correlated model of relative pose uncertainty, and we quantify the resulting improvement in the accuracy of the solutions we obtain relative to state-of-the-art PGO algorithms. Our approach utilizes Riemannian optimization on the planar unit dual quaternion (PUDQ) manifold, and we prove that it converges to first-order stationary points of a Lie-theoretic maximum likelihood objective. Then we show experimentally that, compared to state-of-the-art PGO algorithms, this algorithm produces estimation errors that are lower by 10% to 25% across several orders of magnitude of noise levels and graph sizes.

math.OC↗

arXiv2025

Scalable Distributed Reproduction Numbers of Network Epidemics with Differential Privacy

Reproduction numbers are widely used for the estimation and prediction of epidemic spreading processes over networks. However, conventional reproduction numbers of an overall network do not indicate where an epidemic is spreading. Therefore, we propose a novel notion of local distributed reproduction numbers to capture the spreading behaviors of each node in a network. We first show how to compute them and then use them to derive new conditions under which an outbreak can occur. These conditions are then used to derive new conditions for the existence, uniqueness, and stability of equilibrium states of the underlying epidemic model. Building upon these local distributed reproduction numbers, we define cluster distributed reproduction numbers to model the spread between clusters composed of nodes. Furthermore, we demonstrate that the local distributed reproduction numbers can be aggregated into cluster distributed reproduction numbers at different scales. However, both local and cluster distributed reproduction numbers can reveal the frequency of interactions between nodes in a network, which raises privacy concerns. Thus, we next develop a privacy framework that implements a differential privacy mechanism to provably protect the frequency of interactions between nodes when computing distributed reproduction numbers. Numerical experiments show that, even under differential privacy, the distributed reproduction numbers provide accurate estimates of the epidemic spread while also providing more insights than conventional reproduction numbers.

eess.SY↗

arXiv2023

Anomaly Search Over Many Sequences With Switching Costs

This paper considers the quickest search problem to identify anomalies among large numbers of data streams. These streams can model, for example, disjoint regions monitored by a mobile robot. A particular challenge is a version of the problem in which the experimenter must suffer a cost each time the data stream being sampled changes, such as the time the robot must spend moving between regions. In this paper, we propose an algorithm which accounts for switching costs by varying a confidence threshold that governs when the algorithm switches to a new data stream. Our main contributions are easily computable approximations for both the optimal value of this threshold and the optimal value of the parameter that determines when a stream must be re-sampled. Further, we empirically show (i) a uniform improvement for switching costs of interest and (ii) roughly equivalent performance for small switching costs when comparing to the closest available algorithm.

math.OC↗

arXiv2022

Linear Regularizers Enforce the Strict Saddle Property

Satisfaction of the strict saddle property has become a standard assumption in non-convex optimization, and it ensures that many first-order optimization algorithms will almost always escape saddle points. However, functions exist in machine learning that do not satisfy this property, such as the loss function of a neural network with at least two hidden layers. First-order methods such as gradient descent may converge to non-strict saddle points of such functions, and there do not currently exist any first-order methods that reliably escape non-strict saddle points. To address this need, we demonstrate that regularizing a function with a linear term enforces the strict saddle property, and we provide justification for only regularizing locally, i.e., when the norm of the gradient falls below a certain threshold. We analyze bifurcations that may result from this form of regularization, and then we provide a selection rule for regularizers that depends only on the gradient of an objective function. This rule is shown to guarantee that gradient descent will escape the neighborhoods around a broad class of non-strict saddle points, and this behavior is demonstrated on numerical examples of non-strict saddle points common in the optimization literature.

math.OC↗

arXiv2022

Faster Asynchronous Nonconvex Block Coordinate Descent with Locally Chosen Stepsizes

Distributed nonconvex optimization problems underlie many applications in learning and autonomy, and such problems commonly face asynchrony in agents' computations and communications. When delays in these operations are bounded, they are called partially asynchronous. In this paper, we present an uncoordinated stepsize selection rule for partially asynchronous block coordinate descent that only requires local information to implement, and it leads to faster convergence for a class of nonconvex problems than existing stepsize rules, which require global information in some form. The problems we consider satisfy the error bound condition, and the stepsize rule we present only requires each agent to know (i) a certain type of Lipschitz constant of its block of the gradient of the objective and (ii) the communication delays experienced between it and its neighbors. This formulation requires less information to be available to each agent than existing approaches, typically allows for agents to use much larger stepsizes, and alleviates the impact of stragglers while still guaranteeing convergence to a stationary point. Simulation results provide comparisons and validate the faster convergence attained by the stepsize rule we develop.

math.OC↗

arXiv2020

Totally Asynchronous Large-Scale Quadratic Programming: Regularization, Convergence Rates, and Parameter Selection

Quadratic programs arise in robotics, communications, smart grids, and many other applications. As these problems grow in size, finding solutions becomes more computationally demanding, and new algorithms are needed to efficiently solve them at massive scales. Targeting large-scale problems, we develop a multi-agent quadratic programming framework in which each agent updates only a small number of the total decision variables in a problem. Agents communicate their updated values to each other, though we do not impose any restrictions on the timing with which they do so, nor on the delays in these transmissions. Furthermore, we allow weak parametric coupling among agents, in the sense that they are free to independently choose their step sizes, subject to mild restrictions. We further provide the means for agents to independently regularize the problems they solve, thereby improving convergence properties while preserving agents' independence in selecting parameters and ensuring a global bound on regularization error is satisfied. Larger regularizations accelerate convergence but increase error in the solution obtained, and we quantify the trade off between convergence rates and quality of solutions. Simulation results are presented to illustrate these developments.

math.OC↗

arXiv2019

Differentially Private Controller Synthesis With Metric Temporal Logic Specifications

Privacy is an important concern in various multiagent systems in which data collected from the agents are sensitive. We propose a differentially private controller synthesis approach for multi-agent systems subject to high-level specifications expressed in metric temporal logic (MTL). We consider a setting where each agent sends data to a cloud (computing station) through a set of local hubs and the cloud is responsible for computing the control inputs of the agents. Specifically, each agent adds privacy noise (e.g., Gaussian noise) point-wise in time to its own outputs before sharing them with a local hub. Each local hub runs a Kalman filter to estimate the state of the corresponding agent and periodically sends such state estimates to the cloud. The cloud computes the optimal inputs for each agent subject to an MTL specification. While guaranteeing differential privacy of each agent, the controller is also synthesized to ensure a probabilistic guarantee for satisfying the MTL specification.We provide an implementation of the proposed method on a simulation case study with two Baxter-On-Wheels robots as the agents.

eess.SY↗

arXiv2019

Stability and Sustainability of Resource Consumption Networks

In this paper, we examine both stability and sustainability of a network-based model of natural resource consumption. Stability is studied from a dynamical systems perspective, though we argue that sustainability is a fundamentally different notion from stability in social-ecological systems. Accordingly, we also present a criterion for sustainability that is guided by the existing literature on sustainable development. Assuming a generic social network of consuming agents' interactions, we derive sufficient conditions for both the stability and sustainability of the model as constraints on the network structure itself. We complement these analytical results with numerical simulations and discuss the implications of our findings for policy-making for sustainable resource governance.

math.OC↗

arXiv2018

Stability of Leaderless Resource Consumption Networks

In this paper, we study the global stability properties of a multi-agent model of natural resource consumption that balances ecological and social network components in determining the consumption behavior of a group of agents. The social network is assumed to be leaderless, a condition that ensures that no single node has a greater influence than any other node on the dynamics of the resource consumption. It is shown that any network structure can be made leaderless by the social preferences of the agents. The ecological network component includes a quantification of each agent's environmental concern, which captures each individual agent's threshold for when a resource becomes scarce. We show that leaderlessness and a mild bound on agents' environmental concern are jointly sufficient for global asymptotic stability of the consumption network to a positive consumption value, indicating that appropriately configured networks can continuously consume a resource without driving its value to zero. The behavior of these leaderless resource consumption networks is verified in simulation.

eess.SY↗

arXiv2017

Differential Privacy for Sets in Euclidean Space

As multi-agent systems become more numerous and more data-driven, novel forms of privacy are needed in order to protect data types that are not accounted for by existing privacy frameworks. In this paper, we present a new form of privacy for set-valued data which extends the notion of differential privacy to sets which users want to protect. While differential privacy is typically defined in terms of probability distributions, we show that it is more natural here to define privacy for sets over their capacity functionals, which capture the probability of a random set intersecting some other set. In terms of sets' capacity functionals, we provide a novel definition of differential privacy for set-valued data. Based on this definition, we introduce the Laplacian Perturbation Mechanism (so named because it applies random perturbations to sets), and show that it provides ?-differential privacy as prescribed by our definition. These theoretical results are supported by numerical results, demonstrating the practical applicability of the developments made.

math.OC↗

arXiv2017

On the Connectivity of Unions of Random Graphs

Graph-theoretic tools and techniques have seen wide use in the multi-agent systems literature, and the unpredictable nature of some multi-agent communications has been successfully modeled using random communication graphs. Across both network control and network optimization, a common assumption is that the union of agents' communication graphs is connected across any finite interval of some prescribed length, and some convergence results explicitly depend upon this length. Despite the prevalence of this assumption and the prevalence of random graphs in studying multi-agent systems, to the best of our knowledge, there has not been a study dedicated to determining how many random graphs must be in a union before it is connected. To address this point, this paper solves two related problems. The first bounds the number of random graphs required in a union before its expected algebraic connectivity exceeds the minimum needed for connectedness. The second bounds the probability that a union of random graphs is connected. The random graph model used is the Erdős-Rényi model, and, in solving these problems, we also bound the expectation and variance of the algebraic connectivity of unions of such graphs. Numerical results for several use cases are given to supplement the theoretical developments made.

math.OC↗

arXiv2017

Convergence Rate Estimates for Consensus over Random Graphs

Multi-agent coordination algorithms with randomized interactions have seen use in a variety of settings in the multi-agent systems literature. In some cases, these algorithms can be random by design, as in a gossip-like algorithm, and in other cases they are random due to external factors, as in the case of intermittent communications. Targeting both of these scenarios, we present novel convergence rate estimates for consensus problems solved over random graphs. Established results provide asymptotic convergence in this setting, and we provide estimates of the rate of convergence in two forms. First, we estimate decreases in a quadratic Lyapunov function over time to bound how quickly the agents' disagreement decays, and second we bound the probability of being at least a given distance from the point of agreement. Both estimates rely on (approximately) computing eigenvalues of the expected matrix exponential of a random graph's Laplacian, which we do explicitly in terms of the network's size and edge probability, without assuming that any relationship between them holds. Simulation results are provided to support the theoretical developments made.

math.OC↗

arXiv2016

Asynchronous Multi-Agent Primal-Dual Optimization

We present a framework for asynchronously solving convex optimization problems over networks of agents which are augmented by the presence of a centralized cloud computer. This framework uses a Tikhonov-regularized primal-dual approach in which the agents update the system's primal variables and the cloud updates its dual variables. To minimize coordination requirements placed upon the system, the times of communications and computations among the agents are allowed to be arbitrary, provided they satisfy mild conditions. Communications from the agents to the cloud are likewise carried out without any coordination in their timing. However, we require that the cloud keep the dual variable's value synchronized across the agents, and a counterexample is provided that demonstrates that this level of synchrony is indeed necessary for convergence. Convergence rate estimates are provided in both the primal and dual spaces, and simulation results are presented that demonstrate the operation and convergence of the proposed algorithm.

math.OC↗

arXiv2015

Cloud-Based Centralized/Decentralized Multi-Agent Optimization with Communication Delays

We present and analyze a computational hybrid architecture for performing multi-agent optimization. The optimization problems under consideration have convex objective and constraint functions with mild smoothness conditions imposed on them. For such problems, we provide a primal-dual algorithm implemented in the hybrid architecture, which consists of a decentralized network of agents into which centralized information is occasionally injected, and we establish its convergence properties. To accomplish this, a central cloud computer aggregates global information, carries out computations of the dual variables based on this information, and then distributes the updated dual variables to the agents. The agents update their (primal) state variables and also communicate among themselves with each agent sharing and receiving state information with some number of its neighbors. Throughout, communications with the cloud are not assumed to be synchronous or instantaneous, and communication delays are explicitly accounted for in the modeling and analysis of the system. Experimental results are presented to support the theoretical developments made.

math.OC↗