arXiv subjects

Xianchao Xiu

Publications and source records attributed to Xianchao Xiu.

At least 19 recordsLinked to original sources

arXiv2026

Newton Deep Unfolding for Compressed Sensing

Compressed sensing (CS) reconstructs images from highly limited measurements, but existing deep unfolding methods are typically driven by first-order optimization and weakly exploit the optimization states generated during reconstruction. To address these limitations, we propose a Newton deep unfolding network (NDU-Net), which, to the best of our knowledge, is the first deep unfolding framework that leverages second-order optimization for CS reconstruction. Specifically, NDU-Net introduces a Newton update (NU) module to estimate Newton-type update directions and generate optimization states that characterize the current reconstruction process. Furthermore, a Newton-guided multi-scale prior (MP) module is designed to incorporate these optimization states into multi-scale feature restoration, thereby enabling the learned prior to adapt to the current reconstruction stage. Experimental results under different CS ratios confirm that our proposed NDU-Net achieves promising reconstruction performance and exhibits enhanced robustness. Our code is available at https://github.com/xianchaoxiu/DNU-Net.

cs.CV↗

arXiv2026

Beyond Noise Steering: Dual-Latent Space Reinforcement Learning for Generative Robot Policy

Pretrained generative robot policies learn expressive action priors from demonstrations. However, existing reinforcement learning methods only steer the noisy space but fail to modulate intermediate action representations during the generation process, resulting in performance degradation and inefficiency. To address this limitation, we propose a novel Dual-Latent Space Reinforcement Learning (DLSRL) framework, which complements initial-noise steering with representation-level control inside the frozen generator. Specifically, our actor network predicts two distinct latent variables: an initial-noise latent variable that steers behavior generation, and an action-representation latent variable for intermediate feature modulation. Moreover, this representation latent variable is mapped to adapter features and ingeniously injected into the hidden states of intermediate action tokens via residual connections. Our dual-control design enables direct adjustment of action representations without updating the base policy. Experiments across generative policy architectures and robotic manipulation tasks show that DLSRL effectively accelerates online robot policy adaptation and achieves competitive performance. Our code is available at \href{https://github.com/xianchaoxiu/DLSRL}{https://github.com/xianchaoxiu/DLSRL}.

cs.RO↗

arXiv2026

PICANet: Physics-Informed Cascaded Asymmetric Network for Infrared Small Target Detection

Infrared small target detection (ISTD) is an important research direction in image processing. However, existing methods are limited by severe background noise propagation and target degradation in high-level semantic features. To address these limitations, this paper proposes a plug-and-play physics-informed cascaded asymmetric network, named PICANet. Specifically, we construct a hierarchical prior decoupling module to explicitly extract low-level and high-level physical information, thereby characterizing target features at different levels rather than relying solely on convolutional extraction. Furthermore, a dual-prior interactive fusion module is developed to dynamically refine target representations while suppressing complex background clutter. Unlike previous work, a multi-level cross-feature attention module with the cascaded asymmetric mechanism is introduced to achieve precise alignment between high-level semantics and low-level spatial details. Extensive experiments demonstrate that the proposed PICANet outperforms state-of-the-art ISTD methods, showing satisfactory detection accuracy even against complex backgrounds. Our code is available at https://github.com/xianchaoxiu/PICANet.

cs.CV↗

arXiv2026

OptGraph: Large Language Models Enhanced Evolutionary Optimization Via Graph Retrieval-Augmented Generation

Large language models (LLMs) have emerged as a powerful tool for automated evolutionary optimization, but existing methods remain limited in pattern reuse, error-aware refinement, and retrieval robustness across diverse tasks. To address these limitations, we propose OptGraph, the first optimization agentic workflow that introduces graph retrieval-augmented generation (GraphRAG). Specifically, OptGraph first constructs reusable experience as a typed graph, capturing the relationships among modeling patterns, problem formalization, implementation details, and error corrections. In the inference stage, OptGraph leverages graph neighborhood information to enrich retrieved knowledge, providing structured context to improve modeling, verification, and iterative refinement. Moreover, OptGraph supports adaptive knowledge updates, enabling the distillation of execution traces and verification feedback into reusable graph knowledge without ndertaking LLM parameter tuning. Extensive experiments on benchmark datasets show that our proposed OptGraph achieves an average exact accuracy 8.9% higher than the state-of-the-art prompt-based automated optimization frameworks. Our code has been made available at https://github.com/xianchaoxiu/OptGraph.

math.OC↗

arXiv2026

Vehicle Routing Problem Meets Large Language Models: An Overview and Perspectives

The vehicle routing problem (VRP) is a central optimization problem in artificial intelligence, logistics automation, transportation scheduling, and industrial decision-making. VRP and its variants are NP-hard, and practical routing tasks often combine time windows, vehicle capacities, pickup-and-delivery relations, dynamic requests, and other operational constraints, making both modeling and solving difficult. Large language models (LLMs) provide a flexible interface for routing optimization by processing natural-language requirements, generating code, reasoning over constraints, and interacting with external tools. This survey reviews LLM-driven research on VRP, covering the basic definition, main variants, major solver families, and LLM concepts needed for this topic. Existing studies are organized into three roles: modelers translate natural-language requirements into constraints and modeling code; designers generate heuristics, operators, or route plans; and coordinators organize tool calls, multi-agent collaboration, and connections with neural solvers. The survey also reviews standard benchmarks, real or near-real operational datasets, LLM-oriented evaluation frameworks, and two comparative experiments. The goal is to clarify current progress in LLM-assisted routing optimization and provide a structured reference for intelligent decision-making, advanced manufacturing, and industrial automation.

math.OC↗

arXiv2026

Transformer-Guided Content-Adaptive Graph Learning for Hyperspectral Unmixing

Hyperspectral unmixing (HU) targets to decompose each mixed pixel in remote sensing images into a set of endmembers and their corresponding abundances. Despite significant progress in this field using deep learning, most methods fail to simultaneously characterize global dependencies and local consistency, making it difficult to preserve both long-range interactions and boundary details. This letter proposes a novel transformer-guided content-adaptive graph unmixing framework (T-CAGU), which overcomes these challenges by employing a transformer to capture global dependencies and introducing a content-adaptive graph neural network to enhance local relationships. Unlike previous work, T-CAGU integrates multiple propagation orders to dynamically learn the graph structure, ensuring robustness against noise. Furthermore, T-CAGU leverages a graph residual mechanism to preserve global information and stabilize training. Experimental results demonstrate its superiority over the state-of-the-art methods. Our code is available at https://github.com/xianchaoxiu/T-CAGU.

cs.CV↗

arXiv2026

Large Language Models for Operations Research: A Comprehensive Survey

Operations Research (OR) serves as a core decision-support methodology for complex systems, with significant applications across mathematics, management science, and computer science. Traditional approaches heavily rely on expert knowledge and often struggle to efficiently solve large-scale and multi-constraint problems. The rapid advancement of Large Language Models (LLMs) in recent years has offered a novel research paradigm to address these challenges. This paper presents a systematic survey of Large Language Models for Operations Research (LLM4OR). We begin by introducing the definition of OR problems and the fundamental principles of LLMs. We then focus on analyzing the roles of LLMs in OR, specifically covering such as model formulation, algorithm design, and solution verification. In addition, we discuss practical applications in representative scenarios and summarize benchmark datasets in this field. Finally, we outline the key challenges and provide perspectives on future research directions. A collection of related literature is available at https://github.com/xianchaoxiu/LLM4OR.

math.OC↗

arXiv2026

New Bounds for Exact Penalized Cardinality-Constrained Optimization with Pseudonormality Conditions

Cardinality-constrained optimization (CCO) is a popular topic in sparse learning and signal recovery, yet remains challenging due to the inherent nonconvexity and discontinuity of cardinality constraints. This paper investigates the exact penalty theory for CCO problems with general equality and inequality constraints. In particular, we extend the pseudonormality condition to the cardinality-constrained framework and establish the local exact penalization without imposing Lipschitz continuity on the objective function. We further analyze both the projected subgradient method and its stochastic variant with convergence guarantees for the derived exact penalty formulation. Compared with the existing results, we give some more precise bounds of the iterate sequence and the objective function value.

math.OC↗

arXiv2026

Heaviside Low-Rank Support Matrix Machine

Support matrix machine (SMM) is an emerging classification framework that directly handles matrix-structured observations, thereby avoiding the spatial correlations destroyed by vectorization. However, most existing SMM variants rely on convex or nonconvex surrogate loss functions, which may lead to high sensitivity to noise. To address this issue, we propose a novel Heaviside low-rank SMM model called HL-SMM, which leverages the Heaviside loss instead of the common hinge or ramp losses for robustness. Moreover, the low-rank constraint is adopted to accurately characterize the inherent global structure. In theory, we analyze the Karush-Kuhn-Tucker (KKT) points and rigorously prove the sufficient and necessary conditions. In algorithms, we develop an effective proximal alternating minimization (PAM) scheme, where all subproblems have closed-form solutions. Extensive experiments on benchmark datasets validate that the proposed HL-SMM achieves superior classification accuracy and robustness compared to state-of-the-art methods.

cs.LG↗

arXiv2026

Efficient Personalized Federated PCA with Manifold Optimization for IoT Anomaly Detection

Internet of things (IoT) networks face increasing security threats due to their distributed nature and resource constraints. Although federated learning (FL) has gained prominence as a privacy-preserving framework for distributed IoT environments, current federated principal component analysis (PCA) methods lack the integration of personalization and robustness, which are critical for effective anomaly detection. To address these limitations, we propose an efficient personalized federated PCA (FedEP) method for anomaly detection in IoT networks. The proposed model achieves personalization through introducing local representations with the $\ell_1$-norm for element-wise sparsity, while maintaining robustness via enforcing local models with the $\ell_{2,1}$-norm for row-wise sparsity. To solve this non-convex problem, we develop a manifold optimization algorithm based on the alternating direction method of multipliers (ADMM) with rigorous theoretical convergence guarantees. Experimental results confirm that the proposed FedEP outperforms the state-of-the-art FedPG, achieving excellent F1-scores and accuracy in various IoT security scenarios. Our code will be available at \href{https://github.com/xianchaoxiu/FedEP}{https://github.com/xianchaoxiu/FedEP}.

cs.LG↗

arXiv2025

LLM4FS: Leveraging Large Language Models for Feature Selection

Recent advances in large language models (LLMs) have provided new opportunities for decision-making, particularly in the task of automated feature selection. In this paper, we first comprehensively evaluate LLM-based feature selection methods, covering the state-of-the-art DeepSeek-R1, GPT-o3-mini, and GPT-4.5. Then, we propose a new hybrid strategy called LLM4FS that integrates LLMs with traditional data-driven methods. Specifically, input data samples into LLMs, and directly call traditional data-driven techniques such as random forest and forward sequential selection. Notably, our analysis reveals that the hybrid strategy leverages the contextual understanding of LLMs and the high statistical reliability of traditional data-driven methods to achieve excellent feature selection performance, even surpassing LLMs and traditional data-driven methods. Finally, we point out the limitations of its application in decision-making. Our code is available at https://github.com/xianchaoxiu/LLM4FS.

cs.LG↗

arXiv2025

Sparse Tensor CCA via Manifold Optimization for Multi-View Learning

Tensor canonical correlation analysis (TCCA) has garnered significant attention due to its effectiveness in capturing high-order correlations in multi-view learning. However, existing TCCA methods often underemphasize the characterization of individual structures and lack algorithmic convergence guarantees. In order to deal with these challenges, we propose a novel sparse TCCA model called STCCA-L, which integrates sparse regularization of canonical matrices and Laplacian regularization of multi-order graphs into the TCCA framework, thereby effectively exploiting the geometric structure of individual views. To solve this non-convex model, we develop an efficient alternating manifold proximal gradient algorithm based on manifold optimization, which avoids computationally expensive full tensor decomposition and leverages a semi-smooth Newton method for resolving the subproblem. Furthermore, we rigorously prove the convergence of the algorithm and analyze its complexity. Experimental results on eight benchmark datasets demonstrate the superior classification performance of the proposed method. Notably, on the 3Sources dataset, it achieves improvements of at least 4.50\% in accuracy and 6.77\% in F1 score over competitors. Our code is available at https://github.com/zhudafa/STCCA-L.

math.OC↗

arXiv2025

GoPrune: Accelerated Structured Pruning with $\ell_{2,p}$-Norm Optimization

Convolutional neural networks (CNNs) suffer from rapidly increasing storage and computational costs as their depth grows, which severely hinders their deployment on resource-constrained edge devices. Pruning is a practical approach for network compression, among which structured pruning is the most effective for inference acceleration. Although existing work has applied the $\ell_p$-norm to pruning, it only considers unstructured pruning with $p\in (0, 1)$ and has low computational efficiency. To overcome these limitations, we propose an accelerated structured pruning method called GoPrune. Our method employs the $\ell_{2,p}$-norm for sparse network learning, where the value of $p$ is extended to $[0, 1)$. Moreover, we develop an efficient optimization algorithm based on the proximal alternating minimization (PAM), and the resulting subproblems enjoy closed-form solutions, thus improving compression efficiency. Experiments on the CIFAR datasets using ResNet and VGG models demonstrate the superior performance of the proposed method in network pruning. Our code is available at https://github.com/xianchaoxiu/GoPrune.

cs.CV↗

arXiv2025

Federated Structured Sparse PCA for Anomaly Detection in IoT Networks

Although federated learning has gained prominence as a privacy-preserving framework tailored for distributed Internet of Things (IoT) environments, current federated principal component analysis (PCA) methods lack integration of sparsity, a critical feature for robust anomaly detection. To address this limitation, we propose a novel federated structured sparse PCA (FedSSP) approach for anomaly detection in IoT networks. The proposed model uniquely integrates double sparsity regularization: (1) row-wise sparsity governed by $\ell_{2,p}$-norm with $p\in [0,1)$ to eliminate redundant feature dimensions, and (2) element-wise sparsity via $\ell_{q}$-norm with $q\in [0,1)$ to suppress noise-sensitive components. To solve this nonconvex problem in a distributed setting, we devise an efficient optimization algorithm based on the proximal alternating minimization (PAM). Numerical experiments validate that incorporating structured sparsity enhances both model interpretability and detection accuracy. Our code is available at https://github.com/xianchaoxiu/FedSSP.

cs.LG↗

arXiv2025

A Fast and Convergent Algorithm for Unassigned Distance Geometry Problems

In this paper, we propose a fast and convergent algorithm to solve unassigned distance geometry problems (uDGP). Technically, we construct a novel quadratic measurement model by leveraging $\ell_0$-norm instead of $\ell_1$-norm in the literature. To solve the nonconvex model, we establish its optimality conditions and develop a fast iterative hard thresholding (IHT) algorithm. Theoretically, we rigorously prove that the whole generated sequence converges to the L-stationary point with the help of the Kurdyka-Lojasiewicz (KL) property. Numerical studies on the turnpike and beltway problems validate its superiority over existing $\ell_1$-norm-based method.

math.OC↗

arXiv2025

Data-Adaptive Transformed Bilateral Tensor Low-Rank Representation for Clustering

Tensor low-rank representation (TLRR) has demonstrated significant success in image clustering. However, most existing methods rely on fixed transformations and suffer from poor robustness to noise. In this paper, we propose a novel transformed bilateral tensor low-rank representation model called TBTLRR, which introduces a data-adaptive tensor nuclear norm by learning arbitrary unitary transforms, allowing for more effective capture of global correlations. In addition, by leveraging the bilateral structure of latent tensor data, TBTLRR is able to exploit local correlations between image samples and features. Furthermore, TBTLRR integrates the $\ell_{1/2}$-norm and Frobenius norm regularization terms for better dealing with complex noise in real-world scenarios. To solve the proposed nonconvex model, we develop an efficient optimization algorithm inspired by the alternating direction method of multipliers (ADMM) and provide theoretical convergence. Extensive experiments validate its superiority over the state-of-the-art methods in clustering. The code will be available at https://github.com/xianchaoxiu/TBTLRR.

cs.CV↗

arXiv2025

Lightweight Deep Unfolding Networks with Enhanced Robustness for Infrared Small Target Detection

Infrared small target detection (ISTD) is one of the key techniques in image processing. Although deep unfolding networks (DUNs) have demonstrated promising performance in ISTD due to their model interpretability and data adaptability, existing methods still face significant challenges in parameter lightweightness and noise robustness. In this regard, we propose a highly lightweight framework based on robust principal component analysis (RPCA) called L-RPCANet. Technically, a hierarchical bottleneck structure is constructed to reduce and increase the channel dimension in the single-channel input infrared image to achieve channel-wise feature refinement, with bottleneck layers designed in each module to extract features. This reduces the number of channels in feature extraction and improves the lightweightness of network parameters. Furthermore, a noise reduction module is embedded to enhance the robustness against complex noise. In addition, squeeze-and-excitation networks (SENets) are leveraged as a channel attention mechanism to focus on the varying importance of different features across channels, thereby achieving excellent performance while maintaining both lightweightness and robustness. Extensive experiments on the ISTD datasets validate the superiority of our proposed method compared with state-of-the-art methods covering RPCANet, DRPCANet, and RPCANet++. The code will be available at https://github.com/xianchaoxiu/L-RPCANet.

cs.CV↗

arXiv2025

Adaptive Multi-Order Graph Regularized NMF with Dual Sparsity for Hyperspectral Unmixing

Hyperspectral unmixing (HU) is a critical yet challenging task in remote sensing. However, existing nonnegative matrix factorization (NMF) methods with graph learning mostly focus on first-order or second-order nearest neighbor relationships and usually require manual parameter tuning, which fails to characterize intrinsic data structures. To address the above issues, we propose a novel adaptive multi-order graph regularized NMF method (MOGNMF) with three key features. First, multi-order graph regularization is introduced into the NMF framework to exploit global and local information comprehensively. Second, these parameters associated with the multi-order graph are learned adaptively through a data-driven approach. Third, dual sparsity is embedded to obtain better robustness, i.e., $\ell_{1/2}$-norm on the abundance matrix and $\ell_{2,1}$-norm on the noise matrix. To solve the proposed model, we develop an alternating minimization algorithm whose subproblems have explicit solutions, thus ensuring effectiveness. Experiments on simulated and real hyperspectral data indicate that the proposed method delivers better unmixing results.

cs.CV↗