Searcharxiv⌕ Search

arXiv subjects

Chen An

Publications and source records attributed to Chen An.

8 recordsLinked to original sources
arXiv2026

Diffusion-Guided Cooperative Policy Learning for Target Tracking Based on Underwater Mobile Agent Networks

Multi-agent reinforcement learning (MARL) provides a promising solution for cooperative target tracking in networks of autonomous underwater vehicles (AUVs). However, existing methods still face three major challenges: 1) policy non-stationarity caused by concurrent updates among multiple agents; 2) inefficient policy learning caused by the heterogeneous quality of experiences accumulated during exploration; and 3) policy drift between stochastic exploration and deterministic execution under dynamic underwater disturbances. To address these challenges, this paper develops a four-layer hierarchical MARL architecture comprising global training scheduling, multi-agent coordination, local policy generation, and real-time action execution. Building on this architecture, we propose a Supervised Diffusion-Aided MARL (SDA-MARL) algorithm with three closely coupled mechanisms. First, a dual-decision policy integrates a diffusion-based generative branch with a Deep Deterministic Policy Gradient (DDPG) branch, while segregated experience pools reduce training interference between the two branches. Second, a supervised sample-selection mechanism identifies high-quality tracking transitions and uses their actions to guide reverse diffusion, enabling the generative policy to concentrate on effective regions of the action space. Third, a behavioral-cloning loss transfers diffusion-generated actions to the deterministic DDPG Actor, thereby aligning exploration with execution and suppressing policy drift. Experiments conducted in six-degree-of-freedom underwater environments across multiple AUV-target configurations show that SDA-MARL achieves faster convergence, higher tracking accuracy, more consistent inter-AUV velocities, and shorter tracking paths than the compared MARL methods.

cs.NI↗
arXiv2026

DHEA-MECD: An Embodied Intelligence-Powered DRL Algorithm for AUV Tracking in Underwater Environments with High-Dimensional Features

In recent years, autonomous underwater vehicle (AUV) systems have demonstrated significant potential in complex marine exploration. However, effective AUV-based tracking remains challenging in realistic underwater environments characterized by high-dimensional features, including coupled kinematic states, spatial constraints, time-varying environmental disturbances, etc. To address these challenges, this paper proposes a hierarchical embodied-intelligence (EI) architecture for underwater multi-target tracking with AUVs in complex underwater environments. Built upon this architecture, we introduce the Double-Head Encoder-Attention-based Multi-Expert Collaborative Decision (DHEA-MECD), a novel Deep Reinforcement Learning (DRL) algorithm designed to support efficient and robust multi-target tracking. Specifically, in DHEA-MECD, a Double-Head Encoder-Attention-based information extraction framework is designed to semantically decompose raw sensory observations and explicitly model complex dependencies among heterogeneous features, including spatial configurations, kinematic states, structural constraints, and stochastic perturbations. On this basis, a motion-stage-aware multi-expert collaborative decision mechanism with Top-k expert selection strategy is introduced to support stage-adaptive decision-making. Furthermore, we propose the DHEA-MECD-based underwater multitarget tracking algorithm to enable AUV smart, stable, and anti-interference multi-target tracking. Extensive experimental results demonstrate that the proposed approach achieves superior tracking success rates, faster convergence, and improved motion optimality compared with mainstream DRL-based methods, particularly in complex and disturbance-rich marine environments.

cs.NI↗
arXiv2025

JoPano: Unified Panorama Generation via Joint Modeling

Panorama generation has recently attracted growing interest in the research community, with two core tasks, text-to-panorama and view-to-panorama generation. However, existing methods still face two major challenges: their U-Net-based architectures constrain the visual quality of the generated panoramas, and they usually treat the two core tasks independently, which leads to modeling redundancy and inefficiency. To overcome these challenges, we propose a joint-face panorama (JoPano) generation approach that unifies the two core tasks within a DiT-based model. To transfer the rich generative capabilities of existing DiT backbones learned from natural images to the panorama domain, we propose a Joint-Face Adapter built on the cubemap representation of panoramas, which enables a pretrained DiT to jointly model and generate different views of a panorama. We further apply Poisson Blending to reduce seam inconsistencies that often appear at the boundaries between cube faces. Correspondingly, we introduce Seam-SSIM and Seam-Sobel metrics to quantitatively evaluate the seam consistency. Moreover, we propose a condition switching mechanism that unifies text-to-panorama and view-to-panorama tasks within a single model. Comprehensive experiments show that JoPano can generate high-quality panoramas for both text-to-panorama and view-to-panorama generation tasks, achieving state-of-the-art performance on FID, CLIP-FID, IS, and CLIP-Score metrics.

cs.CV↗
arXiv2023

Cocaine Use Prediction with Tensor-based Machine Learning on Multimodal MRI Connectome Data

This paper considers the use of machine learning algorithms for predicting cocaine use based on magnetic resonance imaging (MRI) connectomic data. The study utilized functional MRI (fMRI) and diffusion MRI (dMRI) data collected from 275 individuals, which was then parcellated into 246 regions of interest (ROIs) using the Brainnetome atlas. After data preprocessing, the datasets were transformed into tensor form. We developed a tensor-based unsupervised machine learning algorithm to reduce the size of the data tensor from $275$ (individuals) $\times 2$ (fMRI and dMRI) $\times 246$ (ROIs) $\times 246$ (ROIs) to $275$ (individuals) $\times 2$ (fMRI and dMRI) $\times 6$ (clusters) $\times 6$ (clusters). This was achieved by applying the high-order Lloyd algorithm to group the ROI data into 6 clusters. Features were extracted from the reduced tensor and combined with demographic features (age, gender, race, and HIV status). The resulting dataset was used to train a Catboost model using subsampling and nested cross-validation techniques, which achieved a prediction accuracy of 0.857 for identifying cocaine users. The model was also compared with other models, and the feature importance of the model was presented. Overall, this study highlights the potential for using tensor-based machine learning algorithms to predict cocaine use based on MRI connectomic data and presents a promising approach for identifying individuals at risk of substance abuse.

stat.AP↗
arXiv2022

A Generalization of Graham's Estimate on the Barban-Vehov Problem

Suppose $\{ \lambda_d\}$ are Selberg's sieve weights and $1 \le w < y \le x$. Graham's estimate on the Barban-Vehov problem shows that $\sum_{1 \le n \le x} (\sum_{d|n} \lambda_d)^2 = \frac{x}{\log(y/w)} + O(\frac{x}{\log^2(y/w)})$. We prove an analogue of this estimate for a sum over ideals of an arbitrary number field $k$. Our asymptotic estimate remains the same; the only difference is that the effective error term may depend on arithmetics of $k$. Our innovation involves multiple counting results on ideals instead of integers. Notably, some of the results are nontrivial generalizations. Furthermore, we prove a corollary that leads to a new zero density estimate.

math.NT↗
arXiv2021

Counterexamples for high-degree generalizations of the Schr\"odinger maximal operator

In 1980 Carleson posed a question on the minimal regularity of an initial data function in a Sobolev space $H^s(\mathbb{R}^n)$ that implies pointwise convergence for the solution of the linear Schr\"odinger equation. After progress by many authors, this was recently resolved (up to the endpoint) by Bourgain, whose counterexample construction for the Schr\"odinger maximal operator proved a necessary condition on the regularity, and Du and Zhang, who proved a sufficient condition. Analogues of Carleson's question remain open for many other dispersive PDE's. We develop a flexible new method to approach such problems, and prove that for any integer $k\geq 2$, if a degree $k$ generalization of the Schr\"odinger maximal operator is bounded from $H^s(\mathbb{R}^n)$ to $L^1(B_n(0,1))$, then $s \geq \frac{1}{4} + \frac{n-1}{4((k-1)n+1)}.$ In dimensions $n \geq 2$, for every degree $k \geq 3$, this is the first result that exceeds a long-standing barrier at $1/4$. Our methods are number-theoretic, and in particular apply the Weil bound, a consequence of the truth of the Riemann Hypothesis over finite fields.

math.CA↗
arXiv2020

Log-free zero density estimates for automorphic $L$-functions

We prove a log-free zero density estimate for automorphic $L$-functions defined over a number field $k$. This work generalizes and sharpens the method of pseudo-characters and the large sieve used earlier by Kowalski and Michel. As applications, we demonstrate for a particular family of number fields of degree $n$ over $k$ (for any $n$) that an effective Chebotarev density theorem and a bound on $\ell$-torsion in class groups hold for almost all fields in the family.

math.NT↗