The Information Bottleneck (IB) method frequently suffers from unstable optimization, characterized by abrupt representation shifts near critical points of the IB trade-off parameter, beta. In this paper, I introduce a novel approach to achieve stable and convex IB optimization through symbolic continuation and entropy-regularized trajectories. I analytically prove convexity and uniqueness of the IB solution path when an entropy regularization term is included, and demonstrate how this stabilizes representation learning across a wide range of \b{eta} values. Additionally, I provide extensive sensitivity analyses around critical points (beta) with statistically robust uncertainty quantification (95% confidence intervals). The open-source implementation, experimental results, and reproducibility framework included in this work offer a clear path for practical deployment and future extension of my proposed method.

The space-air-ground integrated network (SAGIN) has recently emerged as a core element in the 6G networks. However, traditional centralized and synchronous optimization algorithms are unsuitable for SAGIN due to infrastructureless and time-varying environments. This paper aims to develop a novel Asynchronous algorithm a.k.a. Argus for tackling non-convex and non-smooth decentralized federated bilevel learning over SAGIN. The proposed algorithm allows networked agents (e.g. autonomous aerial vehicles) to tackle bilevel learning problems in time-varying networks asynchronously, thereby averting stragglers from impeding the overall training speed. We provide a theoretical analysis of the iteration complexity, communication complexity, and computational complexity of Argus. Its effectiveness is further demonstrated through numerical experiments.

Reinforcement learning (RL) algorithms are increasingly used to solve the optimal power flow (OPF) problem. Yet, the question of how to design RL environments to maximize training performance remains unanswered, both for the OPF and the general case. We propose a general approach for automated RL environment design by utilizing multi-objective optimization. For that, we use the hyperparameter optimization (HPO) framework, which allows the reuse of existing HPO algorithms and methods. On five OPF benchmark problems, we demonstrate that our automated design approach consistently outperforms a manually created baseline environment design. Further, we use statistical analyses to determine which environment design decisions are especially important for performance, resulting in multiple novel insights on how RL-OPF environments should be designed. Finally, we discuss the risk of overfitting the environment to the utilized RL algorithm. To the best of our knowledge, this is the first general approach for automated RL environment design.

A total of more than 3400 public shootings have occurred in the United States between 2016 and 2022. Among these, 25.1% of them took place in an educational institution, 29.4% at the workplace including office buildings, 19.6% in retail store locations, and 13.4% in restaurants and bars. During these critical scenarios, making the right decisions while evacuating can make the difference between life and death. However, emergency evacuation is intensely stressful, which along with the lack of verifiable real-time information may lead to fatal incorrect decisions. To tackle this problem, we developed a multi-route routing optimization algorithm that determines multiple optimal safe routes for each evacuee while accounting for available capacity along the route, thus reducing the threat of crowding and bottlenecking. Overall, our algorithm reduces the total casualties by 34.16% and 53.3%, compared to our previous routing algorithm without capacity constraints and an expert-advised routing strategy respectively. Further, our approach to reduce crowding resulted in an approximate 50% reduction in occupancy in key bottlenecking nodes compared to both of the other evacuation algorithms.

Remote sensing (RS) images are usually produced at an unprecedented scale, yet they are geographically and institutionally distributed, making centralized model training challenging due to data-sharing restrictions and privacy concerns. Federated learning (FL) offers a solution by enabling collaborative model training across decentralized RS data sources without exposing raw data. However, there lacks a realistic federated dataset and benchmark in RS. Prior works typically rely on manually partitioned single dataset, which fail to capture the heterogeneity and scale of real-world RS data, and often use inconsistent experimental setups, hindering fair comparison. To address this gap, we propose a realistic federated RS dataset, termed FedRS. FedRS consists of eight datasets that cover various sensors and resolutions and builds 135 clients, which is representative of realistic operational scenarios. Data for each client come from the same source, exhibiting authentic federated properties such as skewed label distributions, imbalanced client data volumes, and domain heterogeneity across clients. These characteristics reflect practical challenges in federated RS and support evaluation of FL methods at scale. Based on FedRS, we implement 10 baseline FL algorithms and evaluation metrics to construct the comprehensive FedRS-Bench. The experimental results demonstrate that FL can consistently improve model performance over training on isolated data silos, while revealing performance trade-offs of different methods under varying client heterogeneity and availability conditions. We hope FedRS-Bench will accelerate research on large-scale, realistic FL in RS by providing a standardized, rich testbed and facilitating fair comparisons across future works. The source codes and dataset are available at https://fedrs-bench.github.io/.

Reinforcement Learning (RL) has emerged as a powerful tool for neural combinatorial optimization, enabling models to learn heuristics that solve complex problems without requiring expert knowledge. Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast combinatorial action spaces, leading to inefficiency. In this paper, we propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling, emphasizing the superiority among sampled solutions. Methodologically, by reparameterizing the reward function in terms of policy and utilizing preference models, we formulate an entropy-regularized RL objective that aligns the policy directly with preferences while avoiding intractable computations. Furthermore, we integrate local search techniques into the fine-tuning rather than post-processing to generate high-quality preference pairs, helping the policy escape local optima. Empirical results on various benchmarks, such as the Traveling Salesman Problem (TSP), the Capacitated Vehicle Routing Problem (CVRP) and the Flexible Flow Shop Problem (FFSP), demonstrate that our method significantly outperforms existing RL algorithms, achieving superior convergence efficiency and solution quality.

Explainable artificial intelligence (XAI) is essential for trustworthy machine learning (ML), particularly in high-stakes domains such as healthcare and finance. Shapley value (SV) methods provide a principled framework for feature attribution in complex models but incur high computational costs, limiting their scalability in high-dimensional settings. We propose Stochastic Iterative Momentum for Shapley Value Approximation (SIM-Shapley), a stable and efficient SV approximation method inspired by stochastic optimization. We analyze variance theoretically, prove linear $Q$-convergence, and demonstrate improved empirical stability and low bias in practice on real-world datasets. In our numerical experiments, SIM-Shapley reduces computation time by up to 85% relative to state-of-the-art baselines while maintaining comparable feature attribution quality. Beyond feature attribution, our stochastic mini-batch iterative framework extends naturally to a broader class of sample average approximation problems, offering a new avenue for improving computational efficiency with stability guarantees. Code is publicly available at https://github.com/nliulab/SIM-Shapley.

Federated Learning has gained traction in privacy-sensitive collaborative environments, with local SGD emerging as a key optimization method in decentralized settings. While its convergence properties are well-studied, asymptotic statistical guarantees beyond convergence remain limited. In this paper, we present two generalized Gaussian approximation results for local SGD and explore their implications. First, we prove a Berry-Esseen theorem for the final local SGD iterates, enabling valid multiplier bootstrap procedures. Second, motivated by robustness considerations, we introduce two distinct time-uniform Gaussian approximations for the entire trajectory of local SGD. The time-uniform approximations support Gaussian bootstrap-based tests for detecting adversarial attacks. Extensive simulations are provided to support our theoretical results.

This paper presents a novel constrained Factor Graph Optimization (FGO)-based approach for networked inertial navigation in pedestrian localization. To effectively mitigate the drift inherent in inertial navigation solutions, we incorporate kinematic constraints directly into the nonlinear optimization framework. Specifically, we utilize equality constraints, such as Zero-Velocity Updates (ZUPTs), and inequality constraints representing the maximum allowable distance between body-mounted Inertial Measurement Units (IMUs) based on human anatomical limitations. While equality constraints are straightforwardly integrated as error factors, inequality constraints cannot be explicitly represented in standard FGO formulations. To address this, we introduce a differentiable softmax-based penalty term in the FGO cost function to enforce inequality constraints smoothly and robustly. The proposed constrained FGO approach leverages temporal correlations across multiple epochs, resulting in optimal state trajectory estimates while consistently maintaining constraint satisfaction. Experimental results confirm that our method outperforms conventional Kalman filter approaches, demonstrating its effectiveness and robustness for pedestrian navigation.

Coordinating time-sensitive deliveries in environments like hospitals poses a complex challenge, particularly when managing multiple online pickup and delivery requests within strict time windows using a team of heterogeneous robots. Traditional approaches fail to address dynamic rescheduling or diverse service requirements, typically restricting robots to single-task types. This paper tackles the Multi-Pickup and Delivery Problem with Time Windows (MPDPTW), where autonomous mobile robots are capable of handling varied service requests. The objective is to minimize late delivery penalties while maximizing task completion rates. To achieve this, we propose a novel framework leveraging a heterogeneous robot team and an efficient dynamic scheduling algorithm that supports dynamic task rescheduling. Users submit requests with specific time constraints, and our decentralized algorithm, Heterogeneous Mobile Robots Online Diverse Task Allocation (HMR-ODTA), optimizes task assignments to ensure timely service while addressing delays or task rejections. Extensive simulations validate the algorithm's effectiveness. For smaller task sets (40-160 tasks), penalties were reduced by nearly 63%, while for larger sets (160-280 tasks), penalties decreased by approximately 50%. These results highlight the algorithm's effectiveness in improving task scheduling and coordination in multi-robot systems, offering a robust solution for enhancing delivery performance in structured, time-critical environments.