arXiv subjects

Solmaz S. Kia

Publications and source records attributed to Solmaz S. Kia.

At least 19 recordsLinked to original sources

arXiv2026

Adaptive Threshold-Driven Continuous Greedy Method for Scalable Submodular Optimization

Submodular maximization under matroid constraints is a fundamental problem in combinatorial optimization with applications in sensing, data summarization, active learning, and resource allocation. While the Sequential Greedy (SG) algorithm achieves only a $\frac{1}{2}$-approximation due to irrevocable selections, Continuous Greedy (CG) attains the optimal $\bigl(1-\frac{1}{e}\bigr)$-approximation via the multilinear relaxation, at the cost of a progressively dense decision vector that forces agents to exchange feature embeddings for nearly every ground-set element. We propose \textit{ATCG} (\underline{A}daptive \underline{T}hresholded \underline{C}ontinuous \underline{G}reedy), which gates gradient evaluations behind a per-partition progress ratio $η_i$, expanding each agent's active set only when current candidates fail to capture sufficient marginal gain, thereby directly bounding which feature embeddings are ever transmitted. Theoretical analysis establishes a curvature-aware approximation guarantee with effective factor $τ_{\mathrm{eff}}=\max\{τ,1-c\}$, interpolating between the threshold-based guarantee and the low-curvature regime where \textit{ATCG} recovers the performance of CG. This shows that the problem structure, as captured by curvature, determines the amount of coordination and communication required to approach full-CG performance. Experiments on a class-balanced prototype selection problem over a subset of the CIFAR-10 animal dataset show that \textit{ATCG} achieves objective values comparable to those of the full CG method while substantially reducing communication overhead through adaptive active-set expansion.

cs.LG↗

arXiv2026

Scalar Federated Learning for Linear Quadratic Regulator

We propose ScalarFedLQR, a communication-efficient federated algorithm for model-free learning of a common policy in linear quadratic regulator (LQR) control of heterogeneous agents. The method builds on a decomposed projected gradient mechanism, in which each agent communicates only a scalar projection of a local zeroth-order gradient estimate. The server aggregates these scalar messages to reconstruct a global descent direction, reducing per-agent uplink communication from O(d) to O(1), independent of the policy dimension. Crucially, the projection-induced approximation error diminishes as the number of participating agents increases, yielding a favorable scaling law: larger fleets enable more accurate gradient recovery, admit larger stepsizes, and achieve faster linear convergence despite high dimensionality. Under standard regularity conditions, all iterates remain stabilizing and the average LQR cost decreases linearly fast. Numerical results demonstrate performance comparable to full-gradient federated LQR with substantially reduced communication.

eess.SY↗

arXiv2026

A Computationally Efficient Maximum A Posteriori Sequence Estimation via Stein Variational Inference

State estimation in robotic systems presents significant challenges, particularly due to the prevalence of multimodal posterior distributions in real-world scenarios. One effective strategy for handling such complexity is to compute maximum a posteriori (MAP) sequences over a discretized or sampled state space, which enables a concise representation of the most likely state trajectory. However, this approach often incurs substantial computational costs, especially in high-dimensional settings. In this article, we propose a novel MAP sequence estimation method, Stein-MAP-Seq, which effectively addresses multimodality while substantially reducing computational and memory overhead. Our key contribution is a sequential variational inference framework that captures temporal dependencies in dynamical system models and integrates Stein variational gradient descent (SVGD) into a Viterbi-style dynamic programming algorithm, enabling computationally efficient MAP sequence estimation. This integration allows the method to focus computational effort on MAP-consistent modes rather than exhaustively exploring the entire state space. Stein-MAP-Seq inherits the parallelism and mode-seeking behavior of SVGD, allowing particle updates to be efficiently executed on parallel hardware and significantly reducing the number of trajectory candidates required for MAP-sequence recursion compared to conventional methods that rely on hundreds to thousands of particles. We validate the proposed approach on a range of highly multimodal scenarios, including nonlinear dynamics with ambiguous observations, unknown data association with outliers, range-only localization under temporary unobservability, and high-dimensional robotic manipulators. Experimental results demonstrate substantial improvements in estimation accuracy and robustness to multimodality over existing estimation methods.

cs.RO↗

arXiv2025

FedMPDD: Communication-Efficient Federated Learning with Privacy Preservation Attributes via Projected Directional Derivative

This paper introduces \texttt{FedMPDD} (\textbf{Fed}erated Learning via \textbf{M}ulti-\textbf{P}rojected \textbf{D}irectional \textbf{D}erivatives), a novel algorithm that simultaneously optimizes bandwidth utilization and enhances privacy in Federated Learning. The core idea of \texttt{FedMPDD} is to encode each client's high-dimensional gradient by computing its directional derivatives along multiple random vectors. This compresses the gradient into a much smaller message, significantly reducing uplink communication costs from $\mathcal{O}(d)$ to $\mathcal{O}(m)$, where $m \ll d$. The server then decodes the aggregated information by projecting it back onto the same random vectors. Our key insight is that averaging multiple projections overcomes the dimension-dependent convergence limitations of a single projection. We provide a rigorous theoretical analysis, establishing that \texttt{FedMPDD} converges at a rate of $\mathcal{O}(1/\sqrt{K})$, matching the performance of FedSGD. Furthermore, we demonstrate that our method provides some inherent privacy against gradient inversion attacks due to the geometric properties of low-rank projections, offering a tunable privacy-utility trade-off controlled by the number of projections. Extensive experiments on benchmark datasets validate our theory and demonstrates our results.

cs.LG↗

arXiv2025

BEASST: Behavioral Entropic Gradient based Adaptive Source Seeking for Mobile Robots

This paper presents BEASST (Behavioral Entropic Gradient-based Adaptive Source Seeking for Mobile Robots), a novel framework for robotic source seeking in complex, unknown environments. Our approach enables mobile robots to efficiently balance exploration and exploitation by modeling normalized signal strength as a surrogate probability of source location. Building on Behavioral Entropy(BE) with Prelec's probability weighting function, we define an objective function that adapts robot behavior from risk-averse to risk-seeking based on signal reliability and mission urgency. The framework provides theoretical convergence guarantees under unimodal signal assumptions and practical stability under bounded disturbances. Experimental validation across DARPA SubT and multi-room scenarios demonstrates that BEASST consistently outperforms state-of-the-art methods, achieving 15% reduction in path length and 20% faster source localization through intelligent uncertainty-driven navigation that dynamically transitions between aggressive pursuit and cautious exploration.

cs.RO↗

arXiv2025

B-ActiveSEAL: Scalable Uncertainty-Aware Active Exploration with Tightly Coupled Localization-Mapping

Active robot exploration requires decision-making processes that integrate localization and mapping under tightly coupled uncertainty. However, managing these interdependent uncertainties over long-term operations in large-scale environments rapidly becomes computationally intractable. To address this challenge, we propose B-ActiveSEAL, a scalable information-theoretic active exploration framework that explicitly accounts for coupled uncertainties-from perception through mapping-into the decision-making process. Our framework (i) adaptively balances map uncertainty (exploration) and localization uncertainty (exploitation), (ii) accommodates a broad class of generalized entropy measures, enabling flexible and uncertainty-aware active exploration, and (iii) establishes Behavioral entropy (BE) as an effective information measure for active exploration by enabling intuitive and adaptive decision-making under coupled uncertainties. We establish a theoretical foundation for propagating coupled uncertainties and integrating them into general entropy formulations, enabling uncertainty-aware active exploration under tightly coupled localization-mapping. The effectiveness of the proposed approach is validated through rigorous theoretical analysis and extensive experiments on open-source maps and ROS-Unity simulations across diverse and complex environments. The results demonstrate that B-ActiveSEAL achieves a well-balanced exploration-exploitation trade-off and produces diverse, adaptive exploration behaviors across environments, highlighting clear advantages over representative baselines.

cs.RO↗

arXiv2025

NavEX: A Multi-Agent Coverage in Non-Convex and Uneven Environments via Exemplar-Clustering

This paper addresses multi-agent deployment in non-convex and uneven environments. To overcome the limitations of traditional approaches, we introduce Navigable Exemplar-Based Dispatch Coverage (NavEX), a novel dispatch coverage framework that combines exemplar-clustering with obstacle-aware and traversability-aware shortest distances, offering a deployment framework based on submodular optimization. NavEX provides a unified approach to solve two critical coverage tasks: (a) fair-access deployment, aiming to provide equitable service by minimizing agent-target distances, and (b) hotspot deployment, prioritizing high-density target regions. A key feature of NavEX is the use of exemplar-clustering for the coverage utility measure, which provides the flexibility to employ non-Euclidean distance metrics that do not necessarily conform to the triangle inequality. This allows NavEX to incorporate visibility graphs for shortest-path computation in environments with planar obstacles, and traversability-aware RRT* for complex, rugged terrains. By leveraging submodular optimization, the NavEX framework enables efficient, near-optimal solutions with provable performance guarantees for multi-agent deployment in realistic and complex settings, as demonstrated by our simulations.

cs.MA↗

arXiv2025

Submodular Maximization Subject to Uniform and Partition Matroids: From Theory to Practical Applications and Distributed Solutions

This article provides a comprehensive exploration of submodular maximization problems, focusing on those subject to uniform and partition matroids. Crucial for a wide array of applications in fields ranging from computer science to systems engineering, submodular maximization entails selecting elements from a discrete set to optimize a submodular utility function under certain constraints. We explore the foundational aspects of submodular functions and matroids, outlining their core properties and illustrating their application through various optimization scenarios. Central to our exposition is the discussion on algorithmic strategies, particularly the sequential greedy algorithm and its efficacy under matroid constraints. Additionally, we extend our analysis to distributed submodular maximization, highlighting the challenges and solutions for large-scale, distributed optimization problems. This work aims to succinctly bridge the gap between theoretical insights and practical applications in submodular maximization, providing a solid foundation for researchers navigating this intricate domain.

cs.DS↗

arXiv2024

Sequential Gaussian Variational Inference for Nonlinear State Estimation and Its Application in Robot Navigation

Probabilistic state estimation is essential for robots navigating uncertain environments. Accurately and efficiently managing uncertainty in estimated states is key to robust robotic operation. However, nonlinearities in robotic platforms pose significant challenges that require advanced estimation techniques. Gaussian variational inference (GVI) offers an optimization perspective on the estimation problem, providing analytically tractable solutions and efficiencies derived from the geometry of Gaussian space. We propose a Sequential Gaussian Variational Inference (S-GVI) method to address nonlinearity and provide efficient sequential inference processes. Our approach integrates sequential Bayesian principles into the GVI framework, which are addressed using statistical approximations and gradient updates on the information geometry. Validations through simulations and real-world experiments demonstrate significant improvements in state estimation over the Maximum A Posteriori (MAP) estimation method.

cs.RO↗

arXiv2024

Bayesian Online Learning for Human-assisted Target Localization

We consider a human-assisted autonomy sensor fusion for dynamic target localization in a Bayesian framework. Autonomous sensor-based tracking systems can suffer from observability and target detection failure. Humans possess valuable qualitative information derived from their past knowledge and rapid situational awareness that can give them an advantage over machine perception in many scenarios. To compensate for the shortcomings of an autonomous tracking system, we propose to collect spatial sensing information from human operators who visually monitor the target and can provide target localization information in the form of free sketches encircling the area where the target is located. However, human inputs cannot be taken deterministically and trusted absolutely due to their inherent subjectivity and variability. Our focus in this paper is to construct an adaptive probabilistic model for human-provided inputs where the adaptation terms capture the level of reliability of the human inputs. The next contribution of this paper is a novel joint Bayesian learning method to fuse human and autonomous sensor inputs in a manner that the dynamic changes in human detection reliability are also captured and accounted for. Unlike deep learning frameworks, a unique aspect of this Bayesian modeling framework is its analytical closed-form update equations. This feature provides computational efficiency and allows for online learning from limited data sets. Simulations demonstrate our results, underscoring the value of human-machine collaboration in autonomous systems.

cs.RO↗

arXiv2023

Stein Coverage: a Variational Inference Approach to Distribution-matching Multisensor Deployment

This paper examines the spatial coverage optimization problem for multiple sensors in a known convex environment, where the coverage service of each sensor is heterogeneous and anisotropic. We introduce the Stein Coverage algorithm, a distribution-matching coverage approach that aims to place sensors at positions and orientations such that their collective coverage distribution is as close as possible to the event distribution. To select the most important representative points from the coverage event distribution, Stein Coverage utilizes the Stein Variational Gradient Descent (SVGD), a deterministic sampling method from the variational inference literature. An innovation in our work is the introduction of a repulsive force between the samples in the SVGD algorithm to spread the samples and avoid footprint overlap for the deployed sensors. After pinpointing the points of interest for deployment, Stein Coverage solves the multisensor assignment problem using a bipartite optimal matching process. Simulations demonstrate the advantages of the Stein Coverage method compared to conventional Voronoi partitioning multisensor deployment methods.

cs.MA↗

arXiv2022

Distributed Unconstrained Optimization with Time-varying Cost Functions

In this paper, we propose a novel solution for the distributed unconstrained optimization problem where the total cost is the summation of time-varying local cost functions of a group networked agents. The objective is to track the optimal trajectory that minimizes the total cost at each time instant. Our approach consists of a two-stage dynamics, where the first one samples the first and second derivatives of the local costs periodically to construct an estimate of the descent direction towards the optimal trajectory, and the second one uses this estimate and a consensus term to drive local states towards the time-varying solution while reaching consensus. The first part is carried out by the implementation of a weighted average consensus algorithm in the discrete-time framework and the second part is performed with a continuous-time dynamics. Using the Lyapunov stability analysis, an upper bound on the gradient of the total cost is obtained which is asymptotically reached. This bound is characterized by the properties of the local costs. To demonstrate the performance of the proposed method, a numerical example is conducted that studies tuning the algorithm's parameters and their effects on the convergence of local states to the optimal trajectory.

math.OC↗

arXiv2022

Fast model averaging via buffered states and first-order accelerated optimization algorithms

In this letter, we study the problem of accelerating reaching average consensus over connected graphs in a discrete-time communication setting. Literature has shown that consensus algorithms can be accelerated by increasing the graph connectivity or optimizing the weights agents place on the information received from their neighbors. Here, instead of altering the communication graph, we investigate two methods that use buffered states to accelerate reaching average consensus over a given graph. In the first method, we study how convergence rate of the well-known first-order Laplacian average consensus algorithm changes when agreement feedback is generated from buffered states. For this study, we obtain a sufficient condition on the ranges of buffered state that leads to faster convergence. In the second proposed method, we show how the average consensus problem can be cast as a convex optimization problem and solved by first-order accelerated optimization algorithms for strongly-convex cost functions. We construct an accelerated average consensus algorithm using the so-called Triple Momentum optimization algorithm. The first approach requires less global knowledge for choosing the step size, whereas the second one converges faster in our numerical results by using extra information from the graph topology. We demonstrate our results by implementing the proposed algorithms in a Gaussian Mixture Model (GMM) estimation problem used in sensor networks.

math.OC↗

arXiv2022

Online Target Localization using Adaptive Belief Propagation in the HMM Framework

This paper proposes a novel adaptive sample space-based Viterbi algorithm for target localization in an online manner. The method relies on discretizing the target's motion space into cells representing a finite number of hidden states. Then, the most probable trajectory of the tracked target is computed via dynamic programming in a Hidden Markov Model (HMM) framework. The proposed method uses a Bayesian estimation framework which is neither limited to Gaussian noise models nor requires a linearized target motion model or sensor measurement models. However, an HMM-based approach to localization can suffer from poor computational complexity in scenarios where the number of hidden states increases due to high-resolution modeling or target localization in a large space. To improve this poor computational complexity, this paper proposes a belief propagation in the most probable belief space with a low to high-resolution sequentially, reducing the required resources significantly. The proposed method is inspired by the k-d Tree algorithm (e.g., quadtree) commonly used in the computer vision field. Experimental tests using an ultra-wideband (UWB) sensor network demonstrate our results.

cs.RO↗

arXiv2022

The fastest linearly converging discrete-time average consensus using buffered information

In this letter, we study the problem of accelerating reaching average consensus over connected graphs in a discrete-time communication setting. Literature has shown that consensus algorithms can be accelerated by increasing the graph connectivity or optimizing the weights agents place on the information received from their neighbors. In this letter instead of altering the communication graph, we investigate two methods that use buffered states to accelerate reaching average consensus over a given graph. In the first method, we study how convergence rate of the well-known first-order Laplacian average consensus algorithm changes with delayed feedback and obtain a sufficient condition on the ranges of delay that leads to faster convergence. In the second proposed method, we show how average consensus problem can be cast as a convex optimization problem and solved by first-order accelerated optimization algorithms for strongly-convex cost functions. We construct the fastest converging average consensus algorithm using the so-called Triple Momentum optimization algorithm. We demonstrate our results using an in-network linear regression problem, which is formulated as two average consensus problems.

math.OC↗

arXiv2022

Learning Contraction Policies from Offline Data

This paper proposes a data-driven method for learning convergent control policies from offline data using Contraction theory. Contraction theory enables constructing a policy that makes the closed-loop system trajectories inherently convergent towards a unique trajectory. At the technical level, identifying the contraction metric, which is the distance metric with respect to which a robot's trajectories exhibit contraction is often non-trivial. We propose to jointly learn the control policy and its corresponding contraction metric while enforcing contraction. To achieve this, we learn an implicit dynamics model of the robotic system from an offline data set consisting of the robot's state and input trajectories. Using this learned dynamics model, we propose a data augmentation algorithm for learning contraction policies. We randomly generate samples in the state-space and propagate them forward in time through the learned dynamics model to generate auxiliary sample trajectories. We then learn both the control policy and the contraction metric such that the distance between the trajectories from the offline data set and our generated auxiliary sample trajectories decreases over time. We evaluate the performance of our proposed framework on simulated robotic goal-reaching tasks and demonstrate that enforcing contraction results in faster convergence and greater robustness of the learned policy.

cs.LG↗

arXiv2021

Learning-based Measurement Scheduling for Loosely-Coupled Cooperative Localization

In cooperative localization, communicating mobile agents use inter-agent relative measurements to improve their dead-reckoning-based global localization. Measurement scheduling enables an agent to decide which subset of available inter-agent relative measurements it should process when its computational resources are limited. Optimal measurement scheduling is an NP-hard combinatorial optimization problem. The so-called sequential greedy (SG) algorithm is a popular suboptimal polynomial-time solution for this problem. However, the merit function evaluation for the SG algorithms requires access to the state estimate vector and error covariance matrix of all the landmark agents (teammates that an agent can take measurements from). This paper proposes a measurement scheduling for CL that follows the SG approach but reduces the communication and computation cost by using a neural network-based surrogate model as a proxy for the SG algorithm's merit function. The significance of this model is that it is driven by local information and only a scalar metadata from the landmark agents. This solution addresses the time and memory complexity issues of running the SG algorithm in three ways: (a) reducing the inter-agent communication message size, (b) decreasing the complexity of function evaluations by using a simpler surrogate (proxy) function, (c) reducing the required memory size.Simulations demonstrate our results.

cs.RO↗

arXiv2021

Privacy preservation in continuous-time average consensus algorithm via deterministic additive obfuscation signals

This paper considers the problem of privacy preservation against passive internal and external malicious agents in the continuous-time Laplacian average consensus algorithm over strongly connected and weight-balanced digraphs. For this problem, we evaluate the effectiveness of use of additive perturbation signals as a privacy preservation measure against malicious agents that know the graph topology. Our results include (a) identifying the necessary and sufficient conditions on admissible additive perturbation signals that do not perturb the convergence point of the algorithm from the average of initial values of the agents; (b) obtaining the necessary and sufficient condition on the knowledge set of a malicious agent that enables it to identify the initial value of another agent; (c) designing observers that internal and external malicious agents can use to identify the initial conditions of another agent when their knowledge set on that agent enables them to do so. We demonstrate our results through a numerical example.

eess.SY↗