arXiv subjects

Zhanhong Jiang

Publications and source records attributed to Zhanhong Jiang.

At least 19 recordsLinked to original sources

arXiv2026

Continuous-Time Probabilistic Correctors for Uncertainty-Aware Physics-Based Spacecraft Trajectory Forecasting

Long-horizon spacecraft trajectory forecasting suffers from error accumulation due to the absence of corrective observations in the forecast regime, making reliable uncertainty estimation crucial for safety-critical decision-making such as space domain awareness and conjunction assessment. While high-fidelity physics-based orbit propagators provide accurate deterministic forecasts, they typically lack calibrated uncertainty estimates over long horizons. We introduce a Predictor--Corrector framework in which a physics-based continuous-time $\textit{deterministic}$ forecaster is augmented with a learned continuous-time $\textit{probabilistic}$ Corrector that models forecast errors. The proposed Corrector can be wrapped around an existing deterministic propagator to improve forecast accuracy while producing sharp and calibrated full-covariance uncertainty estimates. The Corrector is based on Latent Neural Controlled Differential Equations (Latent NCDEs) and models the probabilistic temporal evolution of forecast errors in continuous time, naturally supporting irregular sampling and missing features. We further introduce a loss function that promotes calibration and sharpness in long-horizon uncertainty propagation. We evaluate the proposed framework on long-horizon spacecraft trajectory forecasting using real-world data from NASA's Crustal Dynamics Data Information System (CDDIS), wrapping the Corrector around NASA's General Mission Analysis Tool (GMAT). Across forecast horizons of 2--4 days without observations and six rolling test windows, the proposed approach consistently improves accuracy and uncertainty calibration compared to deterministic baselines and Latent ODE-based correctors, demonstrating the effectiveness of the continuous-time probabilistic Corrector for trajectory forecasting.

cs.LG↗

arXiv2026

Lighting-aware Unified Model for Instance Segmentation

Foundation models like the Segment Anything Model (SAM) demonstrate impressive zero-shot generalization but frequently degrade under diverse real-world illumination, particularly for instance segmentation. In this work, we address this limitation by developing \textit{Lighting Convolutional-Attention (\lca{})}, an adapter module that enhances segmentation robustness without fine-tuning the heavy backbone. \lca{} employs a dual-branch architecture to process RGB features alongside contrast maps, enabling physically motivated sensitivity to structural changes rather than illumination artifacts. We optimize \lca{} through a pairwise training strategy, introducing a targeted loss term that explicitly penalizes discrepancies between clean images and their corresponding illumination variants. To evaluate and support this architecture, we conduct a comprehensive empirical study across multiple existing benchmarks and present a novel Unity-based synthetic dataset specifically designed to accurately replicate complex real-world lighting conditions. Extensive experimental results demonstrate that our approach successfully bridges the domain gap, delivering superior lighting-robust segmentation.

cs.CV↗

arXiv2026

Distributed Direct Preference Optimization

Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly understood. Direct Preference Optimization (DPO) avoids explicit reward modeling but lacks convergence guarantees under federated and decentralized training, where communication constraints and non-IID preferences fundamentally alter optimization dynamics. We provide the first convergence and time-complexity analysis of DPO in distributed environments. Modeling personalized offline RL with user-specific preference distributions, we characterize the induced global optimization landscape. For federated DPO, we derive convergence rates that quantify the impact of client drift, communication frequency, and preference heterogeneity; for decentralized DPO, we establish convergence over general communication graphs and show how spectral connectivity governs optimization speed and consensus. Empirically, we corroborate our theoretical insights on standard alignment benchmarks, demonstrating that our proposed methods not only enjoy strong theoretical guarantees but also deliver robust and scalable performance in practice. The code base is available here.

cs.LG↗

arXiv2026

COOPO: Cyclic Offline-Online Policy Optimization Algorithm

Offline reinforcement learning struggles with distributional shift and constrained performance due to static dataset limitations, while online RL demands prohibitive environment interactions. The recent advent of hybrid offline-to-online methods bridges these domains but suffers from distribution drift during transitions and catastrophic forgetting of offline knowledge. We introduce COOPO (Cyclic Offline-Online Policy Optimization), a generalized framework that repeatedly cycles between constrained offline training and online fine-tuning. Each cycle first anchors the policy to the dataset via KL-regularized advantage-weighted offline updates to minimize distributional shift and then fine-tunes it online using any policy optimization for stable exploration. Crucially, periodically returning to offline training eliminates forgetting and drift while maximizing dataset reuse. The cyclic behavior also helps reduce the online environment interactions. Theoretically, COOPO achieves better online sample efficiency, surpassing pure online RL, with guaranteed monotonic improvement under standard coverage assumptions. Extensive D4RL benchmarks demonstrate COOPO reduces online interactions versus state-of-the-art hybrids while improving final returns, maintaining robustness across diverse offline algorithms and online optimizers. This looped synergy sets new efficiency and performance standards for adaptive RL.

cs.LG↗

arXiv2026

TabQL: In-Context Q-Learning with Tabular Foundation Models

We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) with a tabular foundation model endowed with in-context learning capabilities. The key idea is to represent Q-values through a sequence-to-sequence foundation model operating over a tabularized representation of state-action-Q-value tuples, enabling rapid adaptation from limited online interaction by conditioning on recent experience. TabQL departs from classical DQN by leveraging (i) zero- or few-shot Q-value inference via in-context updates, and (ii) a warm-up phase using standard DQN to bootstrap high-quality context. Particularly, to enhance the context quality, new transitions are generated by executing actions output by TabQL with predicted Q values from DQN. We formalize TabQL, analyze its convergence and sample complexity under mild assumptions, and show that TabQL interpolates between vanilla Q-learning and DQN with in-context learning. Our analysis demonstrates that TabQL achieves improved efficiency compared to DQN by amortizing Bellman updates through in-context learning. Extensive numerical experiments with several benchmarks showcase the effectiveness and efficacy of the proposed TabQL.

cs.LG↗

arXiv2026

Neural CDEs as Correctors for Learned Time Series Models

Learned time-series models, whether continuous or discrete, are widely used for forecasting the states of dynamical systems but suffer from error accumulation in multi-step forecasts. To address this issue, we propose a Predictor-Corrector framework in which the Predictor is a learned time-series model that generates multi-step forecasts and the Corrector is a neural controlled differential equation that corrects the forecast errors. The Corrector works with irregularly sampled time series and is compatible with both continuous- and discrete-time Predictors. We further introduce two regularization strategies that improve the Corrector's extrapolation performance and accelerate its training. We also provide theoretical guarantees on the stability and convergence of the proposed framework. Experiments on synthetic, physics-based, and real-world datasets show that the proposed framework consistently improves forecasting performance across diverse Predictors, including neural ordinary differential equations, ContiFormer, and DLinear, demonstrating its predictor-agnostic nature.

cs.LG↗

arXiv2026

ADKO: Agentic Decentralized Knowledge Optimization

We present Agentic Decentralized Knowledge Optimization (ADKO), a framework for collaborative black-box optimization across autonomous agents that achieves sample efficiency, privacy preservation, heterogeneous-objective handling, and communication efficiency. Each agent maintains a private Gaussian Process (GP) surrogate trained on local data and communicates only through knowledge tokens-compact, lossy summaries containing directional signals, advantage scores, and optional language-model (LM) insights-without sharing raw data or model parameters. ADKO unifies GP-Upper Confidence Bound (GP-UCB), parallel Bayesian optimization, decentralized learning, and LM-guided discovery. We provide the first formal analysis of dual information loss: token compression, quantified via mutual-information-based fidelity, and LM approximation error, decomposed into bias and stochastic noise. Our main result shows cumulative regret decomposes into GP error, LM bias, LM noise, and compression loss, with necessary and sufficient conditions for sublinear regret. We also propose fidelity-aware token pruning to preserve high-information tokens under memory budget. Experiments on neural architecture search and scientific discovery validate the theory and show consistent improvements over strong baselines.

cs.LG↗

arXiv2026

LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy

Offline safe reinforcement learning (RL) is increasingly important for cyber-physical systems (CPS), where safety violations during training are unacceptable and only pre-collected data are available. Existing offline safe RL methods typically balance reward-safety tradeoffs through constraint relaxation or joint optimization, but they often lack structural mechanisms to prevent safety drift. We propose LexiSafe, a lexicographic offline RL framework designed to preserve safety-aligned behavior. We first develop LexiSafe-SC, a single-cost formulation for standard offline safe RL, and derive safety-violation and performance-suboptimality bounds that together yield sample-complexity guarantees. We then extend the framework to hierarchical safety requirements with LexiSafe-MC, which supports multiple safety costs and admits its own sample-complexity analysis. Empirically, LexiSafe demonstrates reduced safety violations and improved task performance compared to constrained offline baselines. By unifying lexicographic prioritization with structural bias, LexiSafe offers a practical and theoretically grounded approach for safety-critical CPS decision-making.

cs.LG↗

arXiv2025

Balancing Utility and Privacy: Dynamically Private SGD with Random Projection

Stochastic optimization is a pivotal enabler in modern machine learning, producing effective models for various tasks. However, several existing works have shown that model parameters and gradient information are susceptible to privacy leakage. Although Differentially Private SGD (DPSGD) addresses privacy concerns, its static noise mechanism impacts the error bounds for model performance. Additionally, with the exponential increase in model parameters, efficient learning of these models using stochastic optimizers has become more challenging. To address these concerns, we introduce the Dynamically Differentially Private Projected SGD (D2P2-SGD) optimizer. In D2P2-SGD, we combine two important ideas: (i) dynamic differential privacy (DDP) with automatic gradient clipping and (ii) random projection with SGD, allowing dynamic adjustment of the tradeoff between utility and privacy of the model. It exhibits provably sub-linear convergence rates across different objective functions, matching the best available rate. The theoretical analysis further suggests that DDP leads to better utility at the cost of privacy, while random projection enables more efficient model learning. Extensive experiments across diverse datasets show that D2P2-SGD remarkably enhances accuracy while maintaining privacy. Our code is available here.

cs.LG↗

arXiv2025

Decentralized Relaxed Smooth Optimization with Gradient Descent Methods

$L_0$-smoothness, which has been pivotal to advancing decentralized optimization theory, is often fairly restrictive for modern tasks like deep learning. The recent advent of relaxed $(L_0,L_1)$-smoothness condition enables improved convergence rates for gradient methods. Despite centralized advances, its decentralized extension remains unexplored and challenging. In this work, we propose the first general framework for decentralized gradient descent (DGD) under $(L_0,L_1)$-smoothness by introducing novel analysis techniques. For deterministic settings, our method with adaptive clipping achieves the best-known convergence rates for convex/nonconvex functions without prior knowledge of $L_0$ and $L_1$ and bounded gradient assumption. In stochastic settings, we derive complexity bounds and identify conditions for improved complexity bound in convex optimization. The empirical validation with real datasets demonstrates gradient-norm-dependent smoothness, bridging theory and practice for $(L_0,L_1)$-decentralized optimization algorithms.

math.OC↗

arXiv2025

Data-driven Kinematic Modeling in Soft Robots: System Identification and Uncertainty Quantification

Precise kinematic modeling is critical in calibration and controller design for soft robots, yet remains a challenging issue due to their highly nonlinear and complex behaviors. To tackle the issue, numerous data-driven machine learning approaches have been proposed for modeling nonlinear dynamics. However, these models suffer from prediction uncertainty that can negatively affect modeling accuracy, and uncertainty quantification for kinematic modeling in soft robots is underexplored. In this work, using limited simulation and real-world data, we first investigate multiple linear and nonlinear machine learning models commonly used for kinematic modeling of soft robots. The results reveal that nonlinear ensemble methods exhibit the most robust generalization performance. We then develop a conformal kinematic modeling framework for soft robots by utilizing split conformal prediction to quantify predictive position uncertainty, ensuring distribution-free prediction intervals with a theoretical guarantee.

cs.RO↗

arXiv2025

Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning

In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints, utilizing only offline data. Traditional methods often face difficulties in balancing these constraints, leading to either diminished performance or increased safety risks. We address these issues with a novel approach that begins by learning a conservatively safe policy through the use of Conditional Variational Autoencoders, which model the latent safety constraints. Subsequently, we frame this as a Constrained Reward-Return Maximization problem, wherein the policy aims to optimize rewards while complying with the inferred latent safety constraints. This is achieved by training an encoder with a reward-Advantage Weighted Regression objective within the latent constraint space. Our methodology is supported by theoretical analysis, including bounds on policy performance and sample complexity. Extensive empirical evaluation on benchmark datasets, including challenging autonomous driving scenarios, demonstrates that our approach not only maintains safety compliance but also excels in cumulative reward optimization, surpassing existing methods. Additional visualizations provide further insights into the effectiveness and underlying mechanisms of our approach.

cs.LG↗

arXiv2025

DeCAF: Decentralized Consensus-And-Factorization for Low-Rank Adaptation of Foundation Models

Low-Rank Adaptation (LoRA) has emerged as one of the most effective, computationally tractable fine-tuning approaches for training Vision-Language Models (VLMs) and Large Language Models (LLMs). LoRA accomplishes this by freezing the pre-trained model weights and injecting trainable low-rank matrices, allowing for efficient learning of these foundation models even on edge devices. However, LoRA in decentralized settings still remains under explored, particularly for the theoretical underpinnings due to the lack of smoothness guarantee and model consensus interference (defined formally below). This work improves the convergence rate of decentralized LoRA (DLoRA) to match the rate of decentralized SGD by ensuring gradient smoothness. We also introduce DeCAF, a novel algorithm integrating DLoRA with truncated singular value decomposition (TSVD)-based matrix factorization to resolve consensus interference. Theoretical analysis shows TSVD's approximation error is bounded and consensus differences between DLoRA and DeCAF vanish as rank increases, yielding DeCAF's matching convergence rate. Extensive experiments across vision/language tasks demonstrate our algorithms outperform local training and rivals federated learning under both IID and non-IID data distributions.

cs.LG↗

arXiv2025

Bidirectional Linear Recurrent Models for Sequence-Level Multisource Fusion

Sequence modeling is a critical yet challenging task with wide-ranging applications, especially in time series forecasting for domains like weather prediction, temperature monitoring, and energy load forecasting. Transformers, with their attention mechanism, have emerged as state-of-the-art due to their efficient parallel training, but they suffer from quadratic time complexity, limiting their scalability for long sequences. In contrast, recurrent neural networks (RNNs) offer linear time complexity, spurring renewed interest in linear RNNs for more computationally efficient sequence modeling. In this work, we introduce BLUR (Bidirectional Linear Unit for Recurrent network), which uses forward and backward linear recurrent units (LRUs) to capture both past and future dependencies with high computational efficiency. BLUR maintains the linear time complexity of traditional RNNs, while enabling fast parallel training through LRUs. Furthermore, it offers provably stable training and strong approximation capabilities, making it highly effective for modeling long-term dependencies. Extensive experiments on sequential image and time series datasets reveal that BLUR not only surpasses transformers and traditional RNNs in accuracy but also significantly reduces computational costs, making it particularly suitable for real-world forecasting tasks. Our code is available here.

cs.LG↗

arXiv2025

Optimizing Navigation And Chemical Application in Precision Agriculture With Deep Reinforcement Learning And Conditional Action Tree

This paper presents a novel reinforcement learning (RL)-based planning scheme for optimized robotic management of biotic stresses in precision agriculture. The framework employs a hierarchical decision-making structure with conditional action masking, where high-level actions direct the robot's exploration, while low-level actions optimize its navigation and efficient chemical spraying in affected areas. The key objectives of optimization include improving the coverage of infected areas with limited battery power and reducing chemical usage, thus preventing unnecessary spraying of healthy areas of the field. Our numerical experimental results demonstrate that the proposed method, Hierarchical Action Masking Proximal Policy Optimization (HAM-PPO), significantly outperforms baseline practices, such as LawnMower navigation + indiscriminate spraying (Carpet Spray), in terms of yield recovery and resource efficiency. HAM-PPO consistently achieves higher yield recovery percentages and lower chemical costs across a range of infection scenarios. The framework also exhibits robustness to observation noise and generalizability under diverse environmental conditions, adapting to varying infection ranges and spatial distribution patterns.

cs.RO↗

arXiv2025

FUSE: First-Order and Second-Order Unified SynthEsis in Stochastic Optimization

Stochastic optimization methods have actively been playing a critical role in modern machine learning algorithms to deliver decent performance. While numerous works have proposed and developed diverse approaches, first-order and second-order methods are in entirely different situations. The former is significantly pivotal and dominating in emerging deep learning but only leads convergence to a stationary point. However, second-order methods are less popular due to their computational intensity in large-dimensional problems. This paper presents a novel method that leverages both the first-order and second-order methods in a unified algorithmic framework, termed FUSE, from which a practical version (PV) is derived accordingly. FUSE-PV stands as a simple yet efficient optimization method involving a switch-over between first and second orders. Additionally, we develop different criteria that determine when to switch. FUSE-PV has provably shown a smaller computational complexity than SGD and Adam. To validate our proposed scheme, we present an ablation study on several simple test functions and show a comparison with baselines for benchmark datasets.

cs.CV↗

arXiv2025

Enhancing PPO with Trajectory-Aware Hybrid Policies

Proximal policy optimization (PPO) is one of the most popular state-of-the-art on-policy algorithms that has become a standard baseline in modern reinforcement learning with applications in numerous fields. Though it delivers stable performance with theoretical policy improvement guarantees, high variance, and high sample complexity still remain critical challenges in on-policy algorithms. To alleviate these issues, we propose Hybrid-Policy Proximal Policy Optimization (HP3O), which utilizes a trajectory replay buffer to make efficient use of trajectories generated by recent policies. Particularly, the buffer applies the "first in, first out" (FIFO) strategy so as to keep only the recent trajectories to attenuate the data distribution drift. A batch consisting of the trajectory with the best return and other randomly sampled ones from the buffer is used for updating the policy networks. The strategy helps the agent to improve its capability on top of the most recent best performance and in turn reduce variance empirically. We theoretically construct the policy improvement guarantees for the proposed algorithm. HP3O is validated and compared against several baseline algorithms using multiple continuous control environments. Our code is available here.

cs.LG↗

arXiv2025

RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception

Vision-language model (VLM) fine-tuning for application-specific visual grounding based on natural language instructions has become one of the most popular approaches for learning-enabled autonomous systems. However, such fine-tuning relies heavily on high-quality datasets to achieve successful performance in various downstream tasks. Additionally, VLMs often encounter limitations due to insufficient and imbalanced fine-tuning data. To address these issues, we propose a new generalizable framework to improve VLM fine-tuning by integrating it with a reinforcement learning (RL) agent. Our method utilizes the RL agent to manipulate objects within an indoor setting to create synthetic data for fine-tuning to address certain vulnerabilities of the VLM. Specifically, we use the performance of the VLM to provide feedback to the RL agent to generate informative data that efficiently fine-tune the VLM over the targeted task (e.g. spatial reasoning). The key contribution of this work is developing a framework where the RL agent serves as an informative data sampling tool and assists the VLM in order to enhance performance and address task-specific vulnerabilities. By targeting the data sampling process to address the weaknesses of the VLM, we can effectively train a more context-aware model. In addition, generating synthetic data allows us to have precise control over each scene and generate granular ground truth captions. Our results show that the proposed data generation approach improves the spatial reasoning performance of VLMs, which demonstrates the benefits of using RL-guided data generation in vision-language tasks.

cs.CV↗