arXiv subjects

Yong He

Publications and source records attributed to Yong He.

At least 55 records · Page 3Linked to original sources

arXiv2024

Optimizing Cooperative path-finding: A Scalable Multi-Agent RRT* with Dynamic Potential Fields

Cooperative path-finding in multi-agent systems demands scalable solutions to navigate agents from their origins to destinations without conflict. Despite the breadth of research, scalability remains hampered by increased computational demands in complex environments. This study introduces the multi-agent RRT* potential field (MA-RRT*PF), an innovative algorithm that addresses computational efficiency and path-finding efficacy in dense scenarios. MA-RRT*PF integrates a dynamic potential field with a heuristic method, advancing obstacle avoidance and optimizing the expansion of random trees in congested spaces. The empirical evaluations highlight MA-RRT*PF's significant superiority over conventional multi-agent RRT* (MA-RRT*) in dense environments, offering enhanced performance and solution quality without compromising integrity. This work not only contributes a novel approach to the field of cooperative multi-agent path-finding but also offers a new perspective for practical applications in densely populated settings where traditional methods are less effective.

cs.MA↗

arXiv2024

Subgroup Identification with Latent Factor Structure

Subgroup analysis has garnered increasing attention for its ability to identify meaningful subgroups within heterogeneous populations, thereby enhancing predictive power. However, in many fields such as social science and biology, covariates are often highly correlated due to common factors. This correlation poses significant challenges for subgroup identification, an issue that is often overlooked in existing literature. In this paper, we aim to address this gap in the ``diverging dimension" regime by proposing a center-augmented subgroup identification method within the Factor Augmented (sparse) Linear Model framework. This method bridges dimension reduction and sparse regression. Our proposed approach is adaptable to the high cross-sectional dependence among covariates and offers computational advantages with a complexity of $O(nK)$, compared to the $O(n^2)$ complexity of the conventional pairwise fusion penalty method in the literature, where $n$ is the sample size and $K$ is the number of subgroups. We also investigate the asymptotic properties of the oracle estimators under conditions on the minimal distance between group centroids. To implement the proposed approach, we introduce a Difference of Convex functions-based Alternating Direction Method of Multipliers (DC-ADMM) algorithm and demonstrate its convergence to a local minimizer in a finite number of steps. We illustrate the superiority of the proposed method through extensive numerical experiments and a real macroeconomic data example. An \texttt{R} package, \texttt{SILFS}, implementing the method is also available on CRAN.

stat.ME↗

arXiv2024

Large-dimensional Robust Factor Analysis with Group Structure

In this paper, we focus on exploiting the group structure for large-dimensional factor models, which captures the homogeneous effects of common factors on individuals within the same group. In view of the fact that datasets in macroeconomics and finance are typically heavy-tailed, we propose to identify the unknown group structure using the agglomerative hierarchical clustering algorithm and an information criterion with the robust two-step (RTS) estimates as initial values. The loadings and factors are then re-estimated conditional on the identified groups. Theoretically, we demonstrate the consistency of the estimators for both group membership and the number of groups determined by the information criterion. Under finite second moment condition, we provide the convergence rate for the newly estimated factor loadings with group information, which are shown to achieve efficiency gains compared to those obtained without group structure information. Numerical simulations and real data analysis demonstrate the nice finite sample performance of our proposed approach in the presence of both group structure and heavy-tailedness.

stat.ME↗

arXiv2024

Breaking the Length Barrier: LLM-Enhanced CTR Prediction in Long Textual User Behaviors

With the rise of large language models (LLMs), recent works have leveraged LLMs to improve the performance of click-through rate (CTR) prediction. However, we argue that a critical obstacle remains in deploying LLMs for practical use: the efficiency of LLMs when processing long textual user behaviors. As user sequences grow longer, the current efficiency of LLMs is inadequate for training on billions of users and items. To break through the efficiency barrier of LLMs, we propose Behavior Aggregated Hierarchical Encoding (BAHE) to enhance the efficiency of LLM-based CTR modeling. Specifically, BAHE proposes a novel hierarchical architecture that decouples the encoding of user behaviors from inter-behavior interactions. Firstly, to prevent computational redundancy from repeated encoding of identical user behaviors, BAHE employs the LLM's pre-trained shallow layers to extract embeddings of the most granular, atomic user behaviors from extensive user sequences and stores them in the offline database. Subsequently, the deeper, trainable layers of the LLM facilitate intricate inter-behavior interactions, thereby generating comprehensive user embeddings. This separation allows the learning of high-level user representations to be independent of low-level behavior encoding, significantly reducing computational complexity. Finally, these refined user embeddings, in conjunction with correspondingly processed item embeddings, are incorporated into the CTR model to compute the CTR scores. Extensive experimental results show that BAHE reduces training time and memory by five times for CTR models using LLMs, especially with longer user sequences. BAHE has been deployed in a real-world system, allowing for daily updates of 50 million CTR data on 8 A100 GPUs, making LLMs practical for industrial CTR prediction.

cs.IR↗

arXiv2024

Knowledge Transfer across Multiple Principal Component Analysis Studies

Transfer learning has aroused great interest in the statistical community. In this article, we focus on knowledge transfer for unsupervised learning tasks in contrast to the supervised learning tasks in the literature. Given the transferable source populations, we propose a two-step transfer learning algorithm to extract useful information from multiple source principal component analysis (PCA) studies, thereby enhancing estimation accuracy for the target PCA task. In the first step, we integrate the shared subspace information across multiple studies by a proposed method named as Grassmannian barycenter, instead of directly performing PCA on the pooled dataset. The proposed Grassmannian barycenter method enjoys robustness and computational advantages in more general cases. Then the resulting estimator for the shared subspace from the first step is further utilized to estimate the target private subspace in the second step. Our theoretical analysis credits the gain of knowledge transfer between PCA studies to the enlarged eigenvalue gap, which is different from the existing supervised transfer learning tasks where sparsity plays the central role. In addition, we prove that the bilinear forms of the empirical spectral projectors have asymptotic normality under weaker eigenvalue gap conditions after knowledge transfer. When the set of informativesources is unknown, we endow our algorithm with the capability of useful dataset selection by solving a rectified optimization problem on the Grassmann manifold, which in turn leads to a computationally friendly rectified Grassmannian K-means procedure. In the end, extensive numerical simulation results and a real data case concerning activity recognition are reported to support our theoretical claims and to illustrate the empirical usefulness of the proposed transfer learning methods.

stat.ML↗

arXiv2024

Defocus-integration Interferometric Scattering Microscopy for Speckle Suppression and Enhancing Nanoparticle Detection on Substrate

Direct optical detection and imaging of single nanoparticles on substrate in wide field underpin vast applications across different research fields. However, the speckles originating from the unavoidable random surface undulations of the substrate ultimately limit the size of the decipherable nanoparticles by the current optical techniques, including the ultrasensitive interferometric scattering microscopy (iSCAT). Here we report a defocus-integration iSCAT to suppress the speckle noise and to enhance the detection and imaging of single nanoparticles on ultra-flat glass substrate and silicon wafer. In particular, we discover distinct symmetry properties of the scattering phase between the nanoparticle and the surface undulations that cause the speckles. Consequently, we develop the defocus-integration technique to suppress the speckles.We experimentally achieve an enhancement of the signal to noise ratio by 6.9 dB for the nanoparticle detection. We demonstrate that the technique is generally applicable for nanoparticles of various materials and for both low and high refractive-index substrates.

physics.optics↗

arXiv2024

PST: Plant segmentation transformer for 3D point clouds of rapeseed plants at the podding stage

Segmentation of plant point clouds to obtain high-precise morphological traits is essential for plant phenotyping. Although the fast development of deep learning has boosted much research on segmentation of plant point clouds, previous studies mainly focus on the hard voxelization-based or down-sampling-based methods, which are limited to segmenting simple plant organs. Segmentation of complex plant point clouds with a high spatial resolution still remains challenging. In this study, we proposed a deep learning network plant segmentation transformer (PST) to achieve the semantic and instance segmentation of rapeseed plants point clouds acquired by handheld laser scanning (HLS) with the high spatial resolution, which can characterize the tiny siliques as the main traits targeted. PST is composed of: (i) a dynamic voxel feature encoder (DVFE) to aggregate the point features with the raw spatial resolution; (ii) the dual window sets attention blocks to capture the contextual information; and (iii) a dense feature propagation module to obtain the final dense point feature map. The results proved that PST and PST-PointGroup (PG) achieved superior performance in semantic and instance segmentation tasks. For the semantic segmentation, the mean IoU, mean Precision, mean Recall, mean F1-score, and overall accuracy of PST were 93.96%, 97.29%, 96.52%, 96.88%, and 97.07%, achieving an improvement of 7.62%, 3.28%, 4.8%, 4.25%, and 3.88% compared to the second-best state-of-the-art network PAConv. For instance segmentation, PST-PG reached 89.51%, 89.85%, 88.83% and 82.53% in mCov, mWCov, mPerc90, and mRec90, achieving an improvement of 2.93%, 2.21%, 1.99%, and 5.9% compared to the original PG. This study proves that the deep-learning-based point cloud segmentation method has a great potential for resolving dense plant point clouds with complex morphological traits.

cs.CV↗

arXiv2023

Extended Signaling Methods for Reduced Video Decoder Power Consumption Using Green Metadata

In this paper, we discuss one aspect of the latest MPEG standard edition on energy-efficient media consumption, also known as Green Metadata (ISO/IEC 232001-11), which is the interactive signaling for remote decoder-power reduction for peer-to-peer video conferencing. In this scenario, the receiver of a video, e.g., a battery-driven portable device, can send a dedicated request to the sender which asks for a video bitstream representation that is less complex to decode and process. Consequently, the receiver saves energy and extends operating times. We provide an overview on latest studies from the literature dealing with energy-saving aspects, which motivate the extension of the legacy Green Metadata standard. Furthermore, we explain the newly introduced syntax elements and verify their effectiveness by performing dedicated experiments. We show that the integration of these syntax elements can lead to dynamic energy savings of up to 90% for software video decoding and 80% for hardware video decoding, respectively.

eess.IV↗

arXiv2023

AntM$^{2}$C: A Large Scale Dataset For Multi-Scenario Multi-Modal CTR Prediction

Click-through rate (CTR) prediction is a crucial issue in recommendation systems. There has been an emergence of various public CTR datasets. However, existing datasets primarily suffer from the following limitations. Firstly, users generally click different types of items from multiple scenarios, and modeling from multiple scenarios can provide a more comprehensive understanding of users. Existing datasets only include data for the same type of items from a single scenario. Secondly, multi-modal features are essential in multi-scenario prediction as they address the issue of inconsistent ID encoding between different scenarios. The existing datasets are based on ID features and lack multi-modal features. Third, a large-scale dataset can provide a more reliable evaluation of models, fully reflecting the performance differences between models. The scale of existing datasets is around 100 million, which is relatively small compared to the real-world CTR prediction. To address these limitations, we propose AntM$^{2}$C, a Multi-Scenario Multi-Modal CTR dataset based on industrial data from Alipay. Specifically, AntM$^{2}$C provides the following advantages: 1) It covers CTR data of 5 different types of items, providing insights into the preferences of users for different items, including advertisements, vouchers, mini-programs, contents, and videos. 2) Apart from ID-based features, AntM$^{2}$C also provides 2 multi-modal features, raw text and image features, which can effectively establish connections between items with different IDs. 3) AntM$^{2}$C provides 1 billion CTR data with 200 features, including 200 million users and 6 million items. It is currently the largest-scale CTR dataset available. Based on AntM$^{2}$C, we construct several typical CTR tasks and provide comparisons with baseline methods. The dataset homepage is available at https://www.atecup.cn/home.

cs.IR↗

arXiv2023

Robust Tensor Factor Analysis

We consider (robust) inference in the context of a factor model for tensor-valued sequences. We study the consistency of the estimated common factors and loadings space when using estimators based on minimising quadratic loss functions. Building on the observation that such loss functions are adequate only if sufficiently many moments exist, we extend our results to the case of heavy-tailed distributions by considering estimators based on minimising the Huber loss function, which uses an $L_{1}$ -norm weight on outliers. We show that such class of estimators is robust to the presence of heavy tails, even when only the second moment of the data exists. We also propose a modified version of the eigenvalue-ratio principle to estimate the dimensions of the core tensor and show the consistency of the resultant estimators without any condition on the relative rates of divergence of the sample size and dimensions. Extensive numerical studies are conducted to show the advantages of the proposed methods over the state-of-the-art ones especially under the heavy-tailed cases. An import/export dataset of a variety of commodities across multiple countries is analyzed to show the practical usefulness of the proposed robust estimation procedure. An R package ``RTFA" implementing the proposed methods is available on R CRAN.

stat.ME↗

arXiv2023

Al-Based Few-Hydrogen Metal-Bonded Perovskite High-$T_c$ Superconductor Al$_4$H up to 54 K under Atmospheric Pressure

Multi-hydrogen lanthanum hydrides have shown the highest critical temperature $T_c$ at 250-260 K under 170-200 GPa. However, such high pressure is a great challenge for sample preparation and practical application. To address this challenge, we propose a novel design strategy for ambient-pressure high-$T_c$ superconductors by constructing new few-hydrogen metal-bonded perovskite hydrides, such as Al-based superconductor $\rm {Al_4H}$, with better ductility than the well-known multi-hydrogen, cuprate and Fe-based superconductors. Based on the Migdal-Eliashberg theory, we predict that the structurally stable $\rm {Al_4H}$ has a favorable high $T_c$ up to 54 K under atmospheric pressure, similar to SmOFeAs.

cond-mat.supr-con↗

arXiv2023

An Efficient Iterative Least Squares Algorithm for Large-dimensional Matrix Factor Model via Random Projection

The matrix factor model has drawn growing attention for its advantage in achieving two-directional dimension reduction simultaneously for matrix-structured observations. In this paper, we propose a simple iterative least squares algorithm for matrix factor models, in contrast to the Principal Component Analysis (PCA)-based methods in the literature. In detail, we first propose to estimate the latent factor matrices by projecting the observations with two deterministic weight matrices, which are chosen to diversify away the idiosyncratic components. We show that the inferences on factors are still asymptotically valid even if we overestimate both the row/column factor numbers. We then estimate the row/column loading matrices by minimizing the squared loss function under certain identifiability conditions. The resultant estimators of the loading matrices are treated as the new weight/projection matrices and thus the above update procedure can be iteratively performed until convergence. Theoretically, given the true dimensions of the factor matrices, we derive the convergence rates of the estimators for loading matrices and common components at any $s$-th step iteration. Additionally, we propose an eigenvalue-ratio method to estimate the pair of factor numbers consistently. Thorough numerical simulations are conducted to investigate the finite-sample performance of the proposed methods and two real datasets associated with financial portfolios and multinational macroeconomic indices are used to illustrate our algorithm's practical usefulness.

stat.ME↗

arXiv2023

Robust Statistical Inference for Large-dimensional Matrix-valued Time Series via Iterative Huber Regression

Matrix factor model is drawing growing attention for simultaneous two-way dimension reduction of well-structured matrix-valued observations. This paper focuses on robust statistical inference for matrix factor model in the ``diverging dimension" regime. We derive the convergence rates of the robust estimators for loadings, factors and common components under finite second moment assumption of the idiosyncratic errors. In addition, the asymptotic distributions of the estimators are also derived under mild conditions. We propose a rank minimization and an eigenvalue-ratio method to estimate the pair of factor numbers consistently. Numerical studies confirm the iterative Huber regression algorithm is a practical and reliable approach for the estimation of matrix factor model, especially under the cases with heavy-tailed idiosyncratic errors . We illustrate the practical usefulness of the proposed methods by two real datasets, one on financial portfolios and one on the macroeconomic indices of China.

stat.ME↗

arXiv2023

Landsberg curvature of twisted product Finsler metric

Let (M1,F1) and (M2,F2) be two Finsler manifolds. The twisted product Finsler metric of F1 and F2 is a Finsler metric F = (F1^2+ f^2F2^2)^1/2 endowed on the product manifold M1 * M2, where f is a positive smooth function on M1 * M2. In this paper, Landsberg curvature and mean Landsberg curvature of the twisted product Finsler metric are derived. Necessary and sufficient conditions for the twisted product Finsler metric to be Landsberg metric or weakly Landsberg metric are obtained. And it is proved that every twisted product Finsler metric has relatively isotropic Landsberg (resp. relatively isotropic mean Landsberg) curvature if and only if it is a Landsberg (resp. weakly Landsberg) metric.

math.DG↗

arXiv2023

Metal-bonded perovskite lead hydride with phonon-mediated superconductivity up to 46 K under atmospheric pressure

In the search for high-temperature superconductivity in hydrides, a plethora of multi-hydrogen superconductors have been theoretically predicted, and some have been synthesized experimentally under ultrahigh pressures of several hundred GPa. However, the impracticality of these high-pressure methods has been a persistent issue. In response, we propose a new approach to achieve high-temperature superconductivity under atmospheric pressure by implanting hydrogen into lead to create a stable few-hydrogen metal-bonded perovskite, Pb$_4$H. This approach diverges from the popular design methodology of multi-hydrogen covalent high critical temperature ($T_c$) superconductors under ultrahigh pressure. By solving the anisotropic Migdal-Eliashberg (ME) equations, we demonstrate that perovskite Pb$_4$H is a typical phonon-mediated superconductor with a $T_c$ of 46 K, which is six times higher than that of bulk Pb (7.22 K) and higher than that of MgB$_2$ (39 K). The high $T_c$ can be attributed to the strong electron-phonon coupling (EPC) strength of 2.45, which arises from hydrogen implantation in lead that induces several high-frequency optical phonon modes with a relatively large phonon linewidth resulting from H atom vibration. The metallic-bonding in perovskite Pb$_4$H not only improves the structural stability but also guarantees better ductility than the widely investigated multi-hydrogen, iron-based, and cuprate superconductors. These results suggest that there is potential for the exploration of new high-temperature superconductors under atmospheric pressure and may reignite interest in their experimental synthesis soon.

cond-mat.supr-con↗

arXiv2023

Huber Principal Component Analysis for Large-dimensional Factor Models

Factor models have been widely used in economics and finance. However, the heavy-tailed nature of macroeconomic and financial data is often neglected in the existing literature. To address this issue and achieve robustness, we propose an approach to estimate factor loadings and scores by minimizing the Huber loss function, which is motivated by the equivalence of conventional Principal Component Analysis (PCA) and the constrained least squares method in the factor model. We provide two algorithms that use different penalty forms. The first algorithm, which we refer to as Huber PCA, minimizes the $\ell_2$-norm-type Huber loss and performs PCA on the weighted sample covariance matrix. The second algorithm involves an element-wise type Huber loss minimization, which can be solved by an iterative Huber regression algorithm. Our study examines the theoretical minimizer of the element-wise Huber loss function and demonstrates that it has the same convergence rate as conventional PCA when the idiosyncratic errors have bounded second moments. We also derive their asymptotic distributions under mild conditions. Moreover, we suggest a consistent model selection criterion that relies on rank minimization to estimate the number of factors robustly. We showcase the benefits of Huber PCA through extensive numerical experiments and a real financial portfolio selection example. An R package named ``HDRFA" has been developed to implement the proposed robust factor analysis.

stat.ME↗

arXiv2023

Full Point Encoding for Local Feature Aggregation in 3D Point Clouds

Point cloud processing methods exploit local point features and global context through aggregation which does not explicity model the internal correlations between local and global features. To address this problem, we propose full point encoding which is applicable to convolution and transformer architectures. Specifically, we propose Full Point Convolution (FPConv) and Full Point Transformer (FPTransformer) architectures. The key idea is to adaptively learn the weights from local and global geometric connections, where the connections are established through local and global correlation functions respectively. FPConv and FPTransformer simultaneously model the local and global geometric relationships as well as their internal correlations, demonstrating strong generalization ability and high performance. FPConv is incorporated in classical hierarchical network architectures to achieve local and global shape-aware learning. In FPTransformer, we introduce full point position encoding in self-attention, that hierarchically encodes each point position in the global and local receptive field. We also propose a shape aware downsampling block which takes into account the local shape and the global context. Experimental comparison to existing methods on benchmark datasets show the efficacy of FPConv and FPTransformer for semantic segmentation, object detection, classification, and normal estimation tasks. In particular, we achieve state-of-the-art semantic segmentation results of 76% mIoU on S3DIS 6-fold and 72.2% on S3DIS Area5.

cs.CV↗

arXiv2023

DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds

Local features and contextual dependencies are crucial for 3D point cloud analysis. Many works have been devoted to designing better local convolutional kernels that exploit the contextual dependencies. However, current point convolutions lack robustness to varying point cloud density. Moreover, contextual modeling is dominated by non-local or self-attention models which are computationally expensive. To solve these problems, we propose density adaptive convolution, coined DAConv. The key idea is to adaptively learn the convolutional weights from geometric connections obtained from the point density and position. To extract precise context dependencies with fewer computations, we propose an interactive attention module (IAM) that embeds spatial information into channel attention along different spatial directions. DAConv and IAM are integrated in a hierarchical network architecture to achieve local density and contextual direction-aware learning for point cloud analysis. Experiments show that DAConv is significantly more robust to point density compared to existing methods and extensive comparisons on challenging 3D point cloud datasets show that our network achieves state-of-the-art classification results of 93.6% on ModelNet40, competitive semantic segmentation results of 68.71% mIoU on S3DIS and part segmentation results of 86.7% mIoU on ShapeNet.

cs.CV↗