arXiv subjects

Guannan Wang

Publications and source records attributed to Guannan Wang.

15 recordsLinked to original sources

arXiv2026

Understanding and Reducing Metadata-Driven Host Overheads in Sampling-Based GNN Training

Modern deep learning workloads increasingly exhibit dynamic, metadata-driven execution, where runtime-generated information determines memory provisioning and kernel launch decisions. In sampling-based graph neural network (GNN) training, this behavior places the CPU on the critical path, introducing persistent host-device orchestration overhead and frequent GPU-CPU synchronization, which dominate end-to-end runtime when GPU computation is small. Existing approaches, including CUDA Graphs and GPU dynamic parallelism, fail to address this problem because the metadata-driven control loop remains host-mediated, and execution structure varies across iterations. We present ZEROGNN, a system that removes the host from the metadata-driven control loop and enables fully GPU-resident execution under dynamic behavior. ZEROGNN keeps runtime metadata on-device, mediates dynamic execution within a fixed launch structure, and provisions a conservative yet tight execution envelope to restore CUDA Graph replayability. Experiments on sampling-based GNN workloads show that ZEROGNN achieves up to 5.28 x end-to-end speedup, near 100% GPU execution fraction, and memory efficiency comparable to ideal metadata-informed allocation, while enabling strong multi-GPU scaling by eliminating host-side bottlenecks.

cs.DC↗

arXiv2025

Reconstructing Multi-Scale Physical Fields from Extremely Sparse Measurements with an Autoencoder-Diffusion Cascade

Extreme sensor sparsity makes full-field reconstruction a fundamentally ill-posed problem in scientific sensing,where the goal is to infer physical fields from sparse measurements.In this regime,the posterior is severely underconstrained and inherently multimodal,making its approximation highly ill-conditioned.Specifically,deterministic mappings collapse uncertainty,direct conditional learning cannot cover the space of possible observation-conditioned solutions,and likelihood-guided sampling becomes highly sensitive to noise and sensor configurations.These limitations result in unstable posterior estimates and highlight the need for modeling uncertainty in a structural manner.To this end,we propose Cascaded Sensing,a hierarchical framework that restructures posterior inference across scales.Rather than modeling the full-field posterior directly,Cas-Sensing first resolves global structural ambiguity through a deterministic coarse-stage estimator.A neural-operator-based functional autoencoder,trained with masked inputs,maps sparse observations to a coarse-scale structural field,acting analogously to a maximum a posteriori estimator that selects the dominant global configuration.This structural anchor fixes the principal degrees of freedom of the posterior and transforms the problem into a better-conditioned residual inference task.A conditional diffusion model then learns only the refined-scale residual distribution,confining sampling to a stable neighborhood of plausible solutions and suppressing competition among observation-consistent modes.To enhance robustness under varying sensing conditions,we introduce mask-cascade training,which exposes the model to diverse sparse observation patterns through intermediate coarse reconstructions.During inference,manifold-constrained guidance enforces observation consistency as a refinement mechanism rather than a global mode-selection process.

cs.LG↗

arXiv2025

Multivariate Functional Linear Discriminant Analysis: An Application to Inflammatory Bowel Disease Classification

Inflammatory Bowel Disease (IBD), including Crohn's Disease (CD) and Ulcerative Colitis (UC), presents significant public health challenges due to its complex etiology. Motivated by the IBD study of the Integrative Human Microbiome Project, our objective is to identify microbial pathways that distinguish between CD, UC and non-IBD over time. Most current research relies on simplistic analyses that examine one variable or time point at a time, or address binary classification problems, limiting our understanding of the dynamic interactions within the microbiome over time. To address these limitations, we develop a novel functional data analysis approach for discriminant analysis of multivariate functional data that can effectively handle multiple high-dimensional predictors, sparse time points, and categorical outcomes. Our method seeks linear combinations of functions (i.e., discriminant functions) that maximize separation between two or more groups over time. We impose a sparsity-inducing penalty when estimating the discriminant functions, allowing us to identify relevant discriminating variables over time. Applications of our method to the motivating data identified microbial features related to mucin degradation, amino acid metabolism, and peptidoglycan recognition, which are implicated in the progression and development of IBD. Furthermore, our method highlighted the role of multiple vitamin B deficiencies in the context of IBD. By moving beyond traditional analytical frameworks, our innovative approach holds the potential for uncovering clinically meaningful discoveries in IBD research.

stat.AP↗

arXiv2025

Training-Free Inference for High-Resolution Sinogram Completion

High-resolution sinogram completion is critical for computed tomography reconstruction, as missing projections can introduce severe artifacts. While diffusion models provide strong generative priors for this task, their inference cost grows prohibitively with resolution. We propose HRSino, a training-free and efficient diffusion inference approach for high-resolution sinogram completion. By explicitly accounting for spatial heterogeneity in signal characteristics, such as spectral sparsity and local complexity, HRSino allocates inference effort adaptively across spatial regions and resolutions, rather than applying uniform high-resolution diffusion steps. This enables global consistency to be captured at coarse scales while refining local details only where necessary. Experimental results show that HRSino reduces peak memory usage by up to 30.81% and inference time by up to 17.58% compared to the state-of-the-art framework, and maintains completion accuracy across datasets and resolutions.

cs.CV↗

arXiv2024

Nonparametric Density Estimation for Data Scattered on Irregular Spatial Domains: A Likelihood-Based Approach Using Bivariate Penalized Spline Smoothing

Accurately estimating data density is crucial for making informed decisions and modeling in various fields. This paper presents a novel nonparametric density estimation procedure that utilizes bivariate penalized spline smoothing over triangulation for data scattered over irregular spatial domains. The approach is likelihood-based with a regularization term that addresses the roughness of the logarithm of density based on a second-order differential operator. The proposed method offers greater efficiency and flexibility in estimating density over complex domains and has been theoretically supported by establishing the asymptotic convergence rate under mild natural conditions. Through extensive simulation studies and a real-world application that analyzes motor vehicle theft data from Portland City, Oregon, we demonstrate the advantages of the proposed method over existing techniques detailed in the literature.

stat.ME↗

arXiv2024

FCDM: A Physics-Guided Bidirectional Frequency Aware Convolution and Diffusion-Based Model for Sinogram Inpainting

Computed tomography (CT) is widely used in scientific imaging systems such as synchrotron and laboratory-based nano-CT, but acquiring full-view sinograms requires high radiation dose and long scan times. Sparse-view CT reduces this burden but produces incomplete sinograms with structured signal loss, degrading reconstruction quality. Unlike RGB images, sinograms encode globally coupled projections and exhibit directional spectral patterns, making conventional RGB-oriented inpainting methods, including diffusion models, ineffective because they ignore angular dependencies and physical constraints inherent to tomographic data. We propose FCDM, a diffusion-based framework for sinogram restoration that incorporates bidirectional frequency reasoning, angular-aware masking, and physics-guided regularization to preserve global structure and physical plausibility. Experiments on real-world datasets show that FCDM consistently outperforms existing baselines, achieving over 0.93 SSIM and 31 dB PSNR across diverse sparse-view settings.

eess.IV↗

arXiv2024

TSSS: A Novel Triangulated Spherical Spline Smoothing for Surface-based Data

Surface-based data is commonly observed in diverse practical applications spanning various fields. In this paper, we introduce a novel nonparametric method to discover the underlying signals from data distributed on complex surface-based domains. Our approach involves a penalized spline estimator defined on a triangulation of surface patches, which enables effective signal extraction and recovery. The proposed method offers several advantages over existing methods, including superior handling of "leakage" or "boundary effects" over complex domains, enhanced computational efficiency, and potential applications in analyzing sparse and irregularly distributed data on complex objects. We provide rigorous theoretical guarantees for the proposed method, including convergence rates of the estimator in both the $L_2$ and supremum norms, as well as the asymptotic normality of the estimator. We also demonstrate that the convergence rates achieved by our estimation method are optimal within the framework of nonparametric estimation. Furthermore, we introduce a bootstrap method to quantify the uncertainty associated with the proposed estimators accurately. The superior performance of the proposed method is demonstrated through simulation experiments and data applications on cortical surface functional magnetic resonance imaging data and oceanic near-surface atmospheric data.

stat.ME↗

arXiv2023

Nonparametric Regression for 3D Point Cloud Learning

Over the past two decades, we have seen an exponentially increased amount of point clouds collected with irregular shapes in various areas. Motivated by the importance of solid modeling for point clouds, we develop a novel and efficient smoothing tool based on multivariate splines over the tetrahedral partitions to extract the underlying signal and build up a 3D solid model from the point cloud. The proposed smoothing method can denoise or deblur the point cloud effectively and provide a multi-resolution reconstruction of the actual signal. In addition, it can handle sparse and irregularly distributed point clouds and recover the underlying trajectory. The proposed smoothing and interpolation method also provides a natural way of numerosity data reduction. Furthermore, we establish the theoretical guarantees of the proposed method. Specifically, we derive the convergence rate and asymptotic normality of the proposed estimator and illustrate that the convergence rate achieves the optimal nonparametric convergence rate. Through extensive simulation studies and a real data example, we demonstrate the superiority of the proposed method over traditional smoothing methods in terms of estimation accuracy and efficiency of data reduction.

stat.CO↗

arXiv2021

Simultaneous Confidence Corridors for Mean Functions in Functional Data Analysis of Imaging Data

Motivated by recent work involving the analysis of biomedical imaging data, we present a novel procedure for constructing simultaneous confidence corridors for the mean of imaging data. We propose to use flexible bivariate splines over triangulations to handle irregular domain of the images that is common in brain imaging studies and in other biomedical imaging applications. The proposed spline estimators of the mean functions are shown to be consistent and asymptotically normal under some regularity conditions. We also provide a computationally efficient estimator of the covariance function and derive its uniform consistency. The procedure is also extended to the two-sample case in which we focus on comparing the mean functions from two populations of imaging data. Through Monte Carlo simulation studies we examine the finite-sample performance of the proposed method. Finally, the proposed method is applied to analyze brain Positron Emission Tomography (PET) data in two different studies. One dataset used in preparation of this article was obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database.

stat.ME↗

arXiv2021

On Selection of Semiparametric Spatial Regression Models

In this paper, we focus on the variable selection techniques for a class of semiparametric spatial regression models which allow one to study the effects of explanatory variables in the presence of the spatial information. The spatial smoothing problem in the nonparametric part is tackled by means of bivariate splines over triangulation, which is able to deal efficiently with data distributed over irregularly shaped regions. In addition, we develop a unified procedure for variable selection to identify significant covariates under a double penalization framework, and we show that the penalized estimators enjoy the "oracle" property. The proposed method can simultaneously identify non-zero spatially distributed covariates and solve the problem of "leakage" across complex domains of the functional spatial component. To estimate the standard deviations of the proposed estimators for the coefficients, a sandwich formula is developed as well. In the end, Monte Carlo simulation examples and a real data example are provided to illustrate the proposed methodology. All technical proofs are given in the supplementary materials.

stat.ME↗

arXiv2021

Efficient Estimation of Partially Linear Models for Spatial Data over Complex Domain

In this paper, we study the estimation of partially linear models for spatial data distributed over complex domains. We use bivariate splines over triangulations to represent the nonparametric component on an irregular two-dimensional domain. The proposed method is formulated as a constrained minimization problem which does not require constructing finite elements or locally supported basis functions. Thus, it allows an easier implementation of piecewise polynomial representations of various degrees and various smoothness over an arbitrary triangulation. Moreover, the constrained minimization problem is converted into an unconstrained minimization via a QR decomposition of the smoothness constraints, which allows for the development of a fast and efficient penalized least squares algorithm to fit the model. The estimators of the parameters are proved to be asymptotically normal under some regularity conditions. The estimator of the bivariate function is consistent, and its rate of convergence is also established. The proposed method enables us to construct confidence intervals and permits inference for the parameters. The performance of the estimators is evaluated by two simulation examples and by a real data analysis.

math.ST↗

arXiv2021

Multivariate Spline Estimation and Inference for Image-On-Scalar Regression

Motivated by recent data analyses in biomedical imaging studies, we consider a class of image-on-scalar regression models for imaging responses and scalar predictors. We propose using flexible multivariate splines over triangulations to handle the irregular domain of the objects of interest on the images, as well as other characteristics of images. The proposed estimators of the coefficient functions are proved to be root-n consistent and asymptotically normal under some regularity conditions. We also provide a consistent and computationally efficient estimator of the covariance function. Asymptotic pointwise confidence intervals and data-driven simultaneous confidence corridors for the coefficient functions are constructed. Our method can simultaneously estimate and make inferences on the coefficient functions while incorporating spatial heterogeneity and spatial correlation. A highly efficient and scalable estimation algorithm is developed. Monte Carlo simulation studies are conducted to examine the finite-sample performance of the proposed method, which is then applied to the spatially normalized positron emission tomography data of the Alzheimer's Disease Neuroimaging Initiative.

stat.ME↗

arXiv2020

Spatiotemporal Dynamics, Nowcasting and Forecasting of COVID-19 in the United States

Epidemic modeling is an essential tool to understand the spread of the novel coronavirus and ultimately assist in disease prevention, policymaking, and resource allocation. In this article, we establish a state of the art interface between classic mathematical and statistical models and propose a novel space-time epidemic modeling framework to study the spatial-temporal pattern in the spread of infectious disease. We propose a quasi-likelihood approach via the penalized spline approximation and alternatively reweighted least-squares technique to estimate the model. Furthermore, we provide a short-term and long-term county-level prediction of the infected/death count for the U.S. by accounting for the control measures, health service resources, and other local features. Utilizing spatiotemporal analysis, our proposed model enhances the dynamics of the epidemiological mechanism and dissects the spatiotemporal structure of the spreading disease. To assess the uncertainty associated with the prediction, we develop a projection band based on the envelope of the bootstrap forecast paths. The performance of the proposed method is evaluated by a simulation study. We apply the proposed method to model and forecast the spread of COVID-19 at both county and state levels in the United States.

stat.AP↗

arXiv2020

Comparing and Integrating US COVID-19 Data from Multiple Sources with Anomaly Detection and Repairing

Over the past few months, the outbreak of Coronavirus disease (COVID-19) has been expanding over the world. A reliable and accurate dataset of the cases is vital for scientists to conduct related research and for policy-makers to make better decisions. We collect the United States COVID-19 daily reported data from four open sources: the New York Times, the COVID-19 Data Repository by Johns Hopkins University, the COVID Tracking Project at the Atlantic, and the USAFacts, then compare the similarities and differences among them. To obtain reliable data for further analysis, we first examine the cyclical pattern and the following anomalies, which frequently occur in the reported cases: (1) the order dependencies violation, (2) the point or period anomalies, and (3) the issue of reporting delay. To address these detected issues, we propose the corresponding repairing methods and procedures if corrections are necessary. In addition, we integrate the COVID-19 reported cases with the county-level auxiliary information of the local features from official sources, such as health infrastructure, demographic, socioeconomic, and environmental information, which are also essential for understanding the spread of the virus.

stat.AP↗

arXiv2019

Experimental analyses on 2-hop-based and 3-hop-based link prediction algorithms

Link prediction is a significant and challenging task in network science. The majority of known methods are similarity-based, which assign similarity indices for node pairs and assume that two nodes of larger similarity have higher probability to be connected by a link. Due to their simplicity, interpretability and high efficiency, similarity-based methods, in particular those based only on local information, have already found successful applications on disparate fields. In this research domain, an intuitive consensus is that two nodes sharing common neighbors are very likely to have a link, while some recent evidences argue that the number of 3-hop paths more accurately predicts missing links than the number of common neighbors. In this paper, we implement extensive experimental comparisons between 2-hop-based and 3-hop-based similarity indices on 128 real networks. Our results indicate that the 3-hop-based indices perform slightly better with a winning rate about 55.88%, but which index is the best one still depends on the target network. Overall speaking, the class of Cannistraci-Hebb indices performs the best among all considered candidates.

physics.soc-ph↗