arXiv subjects

Chenguang Liu

Publications and source records attributed to Chenguang Liu.

At least 19 recordsLinked to original sources

arXiv2026

Uniform-in-time relative entropy estimates for Kac's approximation of the Landau equation

We prove uniform-in-time quantitative relative entropy estimates for Kac's particle approximation of the three-dimensional spatially homogeneous Landau equation for Maxwellian molecules. Using the relative entropy method and logarithmic derivative estimates, we obtain a finite-time normalized entropy bound of order $N^{-1/2}$. The proof relies on explicit covariance identities and a new law-of-large-numbers estimate for the particle system using a new duality method. The uniform-in-time propagation of chaos is derived from an interpolation with an algebraic relaxation estimate toward equilibrium.

math.AP↗

arXiv2026

Quantitative propagation of chaos for the Boltzmann equation with moderately soft potentials

We study the Kac particle system associated with the spatially homogeneous Boltzmann equation with non-cutoff collision kernels in the moderately soft potential regime $-1<\gamma<0$. We prove uniqueness in law for the particle system and, in particular, establish an explicit convergence rate from the empirical measure of the Kac particle system to the weak solution of the Boltzmann equation in Wasserstein-2 distance, assuming that the initial datum $f_0$ has finite Fisher information and polynomial moments. To the best of our knowledge, this provides the first quantitative convergence rate for the Kac particle system in the soft potential setting.

math.AP↗

arXiv2026

Central limit theorem for a partially observed interacting system of Hawkes processes I: subcritical case

We consider a system of $N$ Hawkes processes and observe the actions of a subpopulation of size $K \le N$ up to time $t$, where $K$ is large. The influence relationships between each pair of individuals are modeled by i.i.d.Bernoulli($p$) random variables, where $p \in [0,1]$ is an unknown parameter. Each individual acts at a {\it baseline} rate $\mu > 0$ and, additionally, at an {\it excitation} rate of the form $N^{-1} \sum_{j=1}^{N} \theta_{ij} \int_{0}^{t} \phi(t-s)\,dZ_s^{j,N}$, which depends on the past actions of all individuals that influence it, scaled by $N^{-1}$ (i.e. the mean-field type), with the influence of older actions discounted through a memory kernel $\phi \colon \mathbb{R}{+} \to \mathbb{R}{+}$. Here, $\mu$ and $\phi$ are treated as nuisance parameters. The aim of this paper is to establish a central limit theorem for the estimator of $p$ proposed in \cite{D}, under the subcritical condition $\Lambda p < 1$.

math.PR↗

arXiv2025

Convergence of the generalization error for deep gradient flow methods for PDEs

The aim of this article is to provide a firm mathematical foundation for the application of deep gradient flow methods (DGFMs) for the solution of (high-dimensional) partial differential equations (PDEs). We decompose the generalization error of DGFMs into an approximation and a training error. We first show that the solution of PDEs that satisfy reasonable and verifiable assumptions can be approximated by neural networks, thus the approximation error tends to zero as the number of neurons tends to infinity. Then, we derive the gradient flow that the training process follows in the ``wide network limit'' and analyze the limit of this flow as the training time tends to infinity. These results combined show that the generalization error of DGFMs tends to zero as the number of neurons and the training time tend to infinity.

math.NA↗

arXiv2025

An asymptotically compatible bond-based peridynamics with Gaussian kernel

In this paper, we introduce a novel bond-based peridynamic model that utilizes a Gaussian kernel function. Previous peridynamic models, when directly discretized, have exhibited a lack of asymptotically compatibility with their corresponding local elastic solutions. Additionally, these models have faced challenges in accurately computing the volume of intersecting regions between the horizon of the material point and its neighboring cells. These difficulties in numerical simulations within peridynamics have spurred numerous efforts to develop corrective numerical methods. While such corrective methods have addressed certain issues, they remain complex to formulate and computationally intensive. Instead of addressing these challenges through modified numerical discretization, this paper presents a novel approach: bond-based peridynamics with a Gaussian kernel . This model replaces the bounded kernel function commonly used in existing peridynamic models with an unbounded Gaussian kernel function. Through direct meshfree discretization, we demonstrate that the solution of the proposed model , without the need for compatibility correction or volume correction, aligns with the corresponding local elastic solution. Furthermore, we derive the relevant material parameters based on energy equivalence to an elastic continuum model. Building upon this foundation, we propose a damage model and a linearized version of the proposed peridynamic model. We validate our proposed model through simulations of 2D smooth problems, demonstrating its convergence and accuracy. Finally, we assess the applicability of our approach to realistic scenarios by predicting displacements caused by a 2D plate with pre-existing cracks and replicating high-velocity impact results from the Kalthoff-Winkler experiments.

math-ph↗

arXiv2025

Adaptive Dual-Constrained Line Aggregation for Cross-Paradigm Line Segment Detection

Line segment detection has been studied for decades, yet existing methods are typically designed for different detection paradigms. Generic line segment detectors aim to recover all meaningful line segments in an image, whereas recent deep-learning-based approaches mainly target wireframe line segments that describe salient geometric structures. Because these paradigms follow different detection objectives, methods optimized for one often perform poorly on the other. In this work, we propose Adaptive Dual-Constrained Line Aggregation (ADLA), a line extraction framework designed to operate across different line segment detection paradigms. Starting from an edge strength map, ADLA progressively aggregates pixels into candidate line segments under two complementary geometric constraints: orientation coherence and bounded orthogonal distance to an adaptively estimated line model. During aggregation, the line centroid and orientation are dynamically updated using the accumulated supporting pixels, progressively improving the geometric consistency of the estimated line. Edge strength information is further incorporated into orientation estimation, seed selection, model refinement, and segment validation, reducing the need for extensive parameter tuning. Experiments on three publicly available datasets covering generic, wireframe, and Manhattan line segment detection demonstrate consistently strong performance across substantially different annotation settings. ADLA achieves (F^H) scores of 0.8665 on YorkUrban-LineSegment dataset, 0.8720 on ShanghaiTech dataset, and 0.7297 on YorkUrban dataset. These results demonstrate the effectiveness and flexibility of ADLA across different line segment detection paradigms. The source code for this work is publicly available at https://github.com/ChenguangTelecom/adla .

cs.CV↗

arXiv2025

De-Simplifying Pseudo Labels to Enhancing Domain Adaptive Object Detection

Despite its significant success, object detection in traffic and transportation scenarios requires time-consuming and laborious efforts in acquiring high-quality labeled data. Therefore, Unsupervised Domain Adaptation (UDA) for object detection has recently gained increasing research attention. UDA for object detection has been dominated by domain alignment methods, which achieve top performance. Recently, self-labeling methods have gained popularity due to their simplicity and efficiency. In this paper, we investigate the limitations that prevent self-labeling detectors from achieving commensurate performance with domain alignment methods. Specifically, we identify the high proportion of simple samples during training, i.e., the simple-label bias, as the central cause. We propose a novel approach called De-Simplifying Pseudo Labels (DeSimPL) to mitigate the issue. DeSimPL utilizes an instance-level memory bank to implement an innovative pseudo label updating strategy. Then, adversarial samples are introduced during training to enhance the proportion. Furthermore, we propose an adaptive weighted loss to avoid the model suffering from an abundance of false positive pseudo labels in the late training period. Experimental results demonstrate that DeSimPL effectively reduces the proportion of simple samples during training, leading to a significant performance improvement for self-labeling detectors. Extensive experiments conducted on four benchmarks validate our analysis and conclusions.

cs.CV↗

arXiv2025

Coop-WD: Cooperative Perception with Weighting and Denoising for Robust V2V Communication

Cooperative perception, leveraging shared information from multiple vehicles via vehicle-to-vehicle (V2V) communication, plays a vital role in autonomous driving to alleviate the limitation of single-vehicle perception. Existing works have explored the effects of V2V communication impairments on perception precision, but they lack generalization to different levels of impairments. In this work, we propose a joint weighting and denoising framework, Coop-WD, to enhance cooperative perception subject to V2V channel impairments. In this framework, the self-supervised contrastive model and the conditional diffusion probabilistic model are adopted hierarchically for vehicle-level and pixel-level feature enhancement. An efficient variant model, Coop-WD-eco, is proposed to selectively deactivate denoising to reduce processing overhead. Rician fading, non-stationarity, and time-varying distortion are considered. Simulation results demonstrate that the proposed Coop-WD outperforms conventional benchmarks in all types of channels. Qualitative analysis with visual examples further proves the superiority of our proposed method. The proposed Coop-WD-eco achieves up to 50% reduction in computational cost under severe distortion while maintaining comparable accuracy as channel conditions improve.

cs.CV↗

arXiv2025

Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation

Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far been unevaluated. In this work, we present the systematic review of VLM-based detection and segmentation, view VLM as the foundational model and conduct comprehensive evaluations across multiple downstream tasks for the first time: 1) The evaluation spans eight detection scenarios (closed-set detection, domain adaptation, crowded objects, etc.) and eight segmentation scenarios (few-shot, open-world, small object, etc.), revealing distinct performance advantages and limitations of various VLM architectures across tasks. 2) As for detection tasks, we evaluate VLMs under three finetuning granularities: \textit{zero prediction}, \textit{visual fine-tuning}, and \textit{text prompt}, and further analyze how different finetuning strategies impact performance under varied task. 3) Based on empirical findings, we provide in-depth analysis of the correlations between task characteristics, model architectures, and training methodologies, offering insights for future VLM design. 4) We believe that this work shall be valuable to the pattern recognition experts working in the fields of computer vision, multimodal learning, and vision foundation models by introducing them to the problem, and familiarizing them with the current status of the progress while providing promising directions for future research. A project associated with this review and evaluation has been created at https://github.com/better-chao/perceptual_abilities_evaluation.

cs.CV↗

arXiv2025

DRAMA: A Dynamic Packet Routing Algorithm using Multi-Agent Reinforcement Learning with Emergent Communication

The continuous expansion of network data presents a pressing challenge for conventional routing algorithms. As the demand escalates, these algorithms are struggling to cope. In this context, reinforcement learning (RL) and multi-agent reinforcement learning (MARL) algorithms emerge as promising solutions. However, the urgency and importance of the problem are clear, as existing RL/MARL-based routing approaches lack effective communication in run time among routers, making it challenging for individual routers to adapt to complex and dynamic changing networks. More importantly, they lack the ability to deal with dynamically changing network topology, especially the addition of the router, due to the non-scalability of their neural networks. This paper proposes a novel dynamic routing algorithm, DRAMA, incorporating emergent communication in multi-agent reinforcement learning. Through emergent communication, routers could learn how to communicate effectively to maximize the optimization objectives. Meanwhile, a new Q-network and graph-based emergent communication are introduced to dynamically adapt to the changing network topology without retraining while ensuring robust performance. Experimental results showcase DRAMA's superior performance over the traditional routing algorithm and other RL/MARL-based algorithms, achieving a higher delivery rate and lower latency in diverse network scenarios, including dynamic network load and topology. Moreover, an ablation experiment validates the prospect of emergent communication in facilitating packet routing.

cs.NI↗

arXiv2025

Integrated Sensing, Communication, and Over-The-Air Control of UAV Swarm Dynamics

Coordinated controlling a large UAV swarm requires significant spectrum resources due to the need for bandwidth allocation per UAV, posing a challenge in resource-limited environments. Over-the-air (OTA) control has emerged as a spectrum-efficient approach, leveraging electromagnetic superposition to form control signals at a base station (BS). However, existing OTA controllers lack sufficient optimization variables to meet UAV swarm control objectives and fail to integrate control with other BS functions like sensing. This work proposes an integrated sensing and OTA control framework (ISAC-OTA) for UAV swarm. The BS performs OTA signal construction (uplink) and dispatch (downlink) while simultaneously sensing objects. Two uplink post-processing methods are developed: a control-centric approach generating closed-form control signals via a feedback-looped OTA control problem, and a sensing-centric method mitigating transmission-induced interference for accurate object sensing. For the downlink, a non-convex problem is formulated and solved to minimize control signal dispatch (transmission) error while maintaining a minimum sensing signal-to-noise ratio (SNR). Simulation results show that the proposed ISAC-OTA controller achieves control performance comparable to the benchmark optimal control algorithm while maintaining high sensing accuracy, despite OTA transmission interference. Moreover, it eliminates the need for per-UAV bandwidth allocation, showcasing a spectrum-efficient method for cooperative control in future wireless systems.

eess.SP↗

arXiv2025

PACF: Prototype Augmented Compact Features for Improving Domain Adaptive Object Detection

In recent years, there has been significant advancement in object detection. However, applying off-the-shelf detectors to a new domain leads to significant performance drop, caused by the domain gap. These detectors exhibit higher-variance class-conditional distributions in the target domain than that in the source domain, along with mean shift. To address this problem, we propose the Prototype Augmented Compact Features (PACF) framework to regularize the distribution of intra-class features. Specifically, we provide an in-depth theoretical analysis on the lower bound of the target features-related likelihood and derive the prototype cross entropy loss to further calibrate the distribution of target RoI features. Furthermore, a mutual regularization strategy is designed to enable the linear and prototype-based classifiers to learn from each other, promoting feature compactness while enhancing discriminability. Thanks to this PACF framework, we have obtained a more compact cross-domain feature space, within which the variance of the target features' class-conditional distributions has significantly decreased, and the class-mean shift between the two domains has also been further reduced. The results on different adaptation settings are state-of-the-art, which demonstrate the board applicability and effectiveness of the proposed approach.

cs.CV↗

arXiv2024

Tensor-involved peridynamics: A unified framework for isotropic and anisotropic materials

In this paper, we introduce tensor involved peridynamics, a unified framework for simulating both isotropic and anisotropic materials. While traditional peridynamics models effectively simulate isotropic materials, they face challenges with anisotropic materials and are prone to instability caused by zero energy modes. Our novel model extend the linear bond based peridynamics framework by incorporating the elastic tensor into the micrmodulus function, thereby ensuring stability for anisotropic materials without the need for additional corrections. For isotropic materials. the model mantains compatibility with conventional bond based peridynamics, assuming Possion's rations of 1/4 in 3D and 1/3 in 2D.Numerical experiments confirm the model's stability and accuracy across various scenarios. Additionally, we introduce a damage model for isotropic materials. validating its performance in predicting crack propagation paths in a 2D plate. The results show superior alignment with experimental date compared to traditional model.

cond-mat.mtrl-sci↗

arXiv2024

Rate of convergence of the Kac particle system for the Boltzmann equation with hard potentials

In this paper, we prove that the Kac stochastic particle system converges to the weak solution of the spatially homogeneous Boltzmann equation for hard potentials and hard spheres. We give, under the initial data with finite exponential moment assumption, an explicit rate of propagation of chaos in squared Wasserstein distance with quadratic cost by using a double coupling technique.

math.PR↗

arXiv2024

Scaling limits for supercritical nearly unstable Hawkes processes

In this paper, we investigate the asymptotic behavior of nearly unstable Hawkes processes whose regression kernel has $L^1$ norm strictly greater than one and close to one as time goes to infinity. We find that,the scaling size determines the scaling behavior of the processes like in \cite{MR3313750}. Specifically,after suitable rescaling, the limit of the sequence of Hawkes processes is deterministic.And also with another appropriate rescaling, the sequence converges in law to an integrated Cox Ingersoll Ross like process. This theoretical result may apply to model the recent COVID19 in epidemiology and in social network.

math.PR↗

arXiv2024

How to beat a Bayesian adversary

Deep neural networks and other modern machine learning models are often susceptible to adversarial attacks. Indeed, an adversary may often be able to change a model's prediction through a small, directed perturbation of the model's input - an issue in safety-critical applications. Adversarially robust machine learning is usually based on a minmax optimisation problem that minimises the machine learning loss under maximisation-based adversarial attacks. In this work, we study adversaries that determine their attack using a Bayesian statistical approach rather than maximisation. The resulting Bayesian adversarial robustness problem is a relaxation of the usual minmax problem. To solve this problem, we propose Abram - a continuous-time particle system that shall approximate the gradient flow corresponding to the underlying learning problem. We show that Abram approximates a McKean-Vlasov process and justify the use of Abram by giving assumptions under which the McKean-Vlasov process finds the minimiser of the Bayesian adversarial robustness problem. We discuss two ways to discretise Abram and show its suitability in benchmark adversarial deep learning experiments.

cs.LG↗

arXiv2024

YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images

Detecting objects from aerial images poses significant challenges due to the following factors: 1) Aerial images typically have very large sizes, generally with millions or even hundreds of millions of pixels, while computational resources are limited. 2) Small object size leads to insufficient information for effective detection. 3) Non-uniform object distribution leads to computational resource wastage. To address these issues, we propose YOLC (You Only Look Clusters), an efficient and effective framework that builds on an anchor-free object detector, CenterNet. To overcome the challenges posed by large-scale images and non-uniform object distribution, we introduce a Local Scale Module (LSM) that adaptively searches cluster regions for zooming in for accurate detection. Additionally, we modify the regression loss using Gaussian Wasserstein distance (GWD) to obtain high-quality bounding boxes. Deformable convolution and refinement methods are employed in the detection head to enhance the detection of small objects. We perform extensive experiments on two aerial image datasets, including Visdrone2019 and UAVDT, to demonstrate the effectiveness and superiority of our proposed approach. Code is available at https://github.com/dawn-ech/YOLC.

cs.CV↗

arXiv2024

Subsampling Error in Stochastic Gradient Langevin Diffusions

The Stochastic Gradient Langevin Dynamics (SGLD) are popularly used to approximate Bayesian posterior distributions in statistical learning procedures with large-scale data. As opposed to many usual Markov chain Monte Carlo (MCMC) algorithms, SGLD is not stationary with respect to the posterior distribution; two sources of error appear: The first error is introduced by an Euler--Maruyama discretisation of a Langevin diffusion process, the second error comes from the data subsampling that enables its use in large-scale data settings. In this work, we consider an idealised version of SGLD to analyse the method's pure subsampling error that we then see as a best-case error for diffusion-based subsampling MCMC methods. Indeed, we introduce and study the Stochastic Gradient Langevin Diffusion (SGLDiff), a continuous-time Markov process that follows the Langevin diffusion corresponding to a data subset and switches this data subset after exponential waiting times. There, we show the exponential ergodicity of SLGDiff and that the Wasserstein distance between the posterior and the limiting distribution of SGLDiff is bounded above by a fractional power of the mean waiting time. We bring our results into context with other analyses of SGLD.

stat.ML↗