arXiv subjects

Yuming Zhang

Publications and source records attributed to Yuming Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Towards Open Science: Monitoring Crustal Deformations in North America

The study of the Earth's behavior has greatly benefited from the widespread deployment of Global Navigation Satellite Systems (GNSS), enabling large-scale monitoring of crustal deformation and long-term geophysical trends. In this work, we focus on the North American region, where complex tectonic activity, particularly along the western margin, requires methods capable of processing and analyzing large collections of GNSS time series distributed across extensive spatial domains. Analyzing the full GNSS network provides a coherent view of deformation across multiple scales, allowing detection of long-wavelength signals, subtle intraplate strain and regionally consistent velocity fields that are difficult to capture through local or subsampled analyses. Despite the availability of such data, existing methodologies remain computationally prohibitive for large-scale analyses across this region (or others). To address this limitation, we introduce a highly scalable framework (implemented in open-source software) that enables inference on crustal deformation across the full North American GNSS network using standard computational resources. The proposed method achieves substantial computational gains while maintaining inferential performance comparable to existing approaches and confirms existing tectonic trends, thereby supporting efficient large-scale monitoring and contributing to ongoing efforts toward "Open Science".

physics.geo-ph↗

arXiv2026

Replacement Learning: Training Neural Networks with Fewer Parameters

End-to-end training with full-depth backpropagation remains the dominant paradigm for optimizing deep neural networks, but its efficiency deteriorates as models grow deeper. Since every block must be executed and differentiated under a single global objective, full-depth BP introduces substantial parameter redundancy, activation-memory cost, and training latency, especially when neighboring layers exhibit highly correlated learning patterns. Directly skipping or removing layers can reduce cost, but often weakens representation capacity or requires architecture-specific reuse designs. In this paper, we propose Replacement Learning (RepL), a training-time paradigm that reduces full-depth redundancy by replacing selected blocks rather than simply discarding them. For each removed block, RepL inserts a lightweight computing layer that synthesizes a surrogate operator from the parameters of its adjacent preceding and succeeding blocks through a learnable transformation, and applies the synthesized operator to the preceding activation. In this way, RepL preserves local contextual continuity while avoiding unnecessary full-layer computation. We instantiate RepL for CNNs and ViTs with tailored parameter-fusion blocks that handle convolutional channels, feature resolutions, and transformer submodules. Extensive experiments on CIFAR-10, SVHN, STL-10, ImageNet, COCO, and CityScapes show that RepL reduces trainable parameters, GPU memory usage, and training time while matching or surpassing standard end-to-end training across classification, detection, and segmentation. Additional results on WikiText-2, transfer learning, inference throughput, checkpointing, stochastic depth, and INT8 quantization further demonstrate its generality and compatibility.

cs.CV↗

arXiv2026

Spherical Mixture Integration for Latent Embedding Alignment across Multi-Source Feature Spaces

Multi-institutional electronic health record (Multi-EHR) data have emerged as a powerful resource for developing predictive models to support clinical decisions and for generating reliable real-world evidence. By aggregating information from diverse patient populations and institutions, they enhance the robustness and generalizability of models and findings. However, analyzing multi-EHR remains challenging because disparate institutions rarely map all data elements to common ontologies, and raw EHR codes are often overly granular and institution-specific, fragmenting representations of the same clinical concept. Hence, integrative analysis must overcome two key hurdles: harmonizing codes with the same clinical meaning (synonymy), and aligning institutional feature spaces. To address these challenges, we propose SMILE, a Spherical Mixture Integration for Latent Embedding alignment across multi-source feature spaces, where embeddings from heterogeneous sources serve as privacy-preserving summaries of clinical concepts and sparse relational pairs provide weak supervision. Synonymy is modeled via a mixture of von Mises-Fisher distributions, yielding unified representations of semantically equivalent raw codes. We develop a composite quasi-likelihood estimator with non-asymptotic error bounds for the latent representations and mixture mean directions and consistent synonym-cluster recovery, quantifying the gains from integrating multiple sources and knowledge-graph information. Simulations and a multi-institutional EHR application demonstrate improved alignment and synonym clustering.

stat.ME↗

arXiv2026

Calibrated Estimation and Inference for Semiparametric Regression Models

We consider a broad class of semiparametric regression models in which the conditional distribution of the response takes the form $f\{Y|\boldsymbol{x}^T\boldsymbol{\beta}+m(z),\phi\}$, known up to a parametric component $\boldsymbol{\beta}$ of diverging dimension $p$, a smooth function $m(\cdot)$, and a dispersion parameter $\phi$. The existing literature on such models has focused on semiparametric efficiency for $\boldsymbol{\beta}$, treating $\phi$ and $m(\cdot)$ as nuisances and largely ignoring finite-sample bias. Yet this bias can be substantial, particularly when $p$ is large relative to $n$ or the dispersion is high, and it can seriously undermine inference for $\boldsymbol{\beta}$; moreover, $\phi$ is often of direct scientific interest. We therefore propose SABRE, a general calibration framework for semiparametric estimation and inference, which calibrates an initial estimator against its model-implied expectation under a tractable parametric approximation to the semiparametric model. For generalized partially linear models, we show that SABRE reduces the bias of both $\boldsymbol{\beta}$ and $\phi$, accommodates a diverging parameter dimension without sparsity, and preserves the first-order variance and semiparametric efficiency of the initial estimator; the joint construction also improves estimation and inference for $m(\cdot)$. Simulation studies and an application to Alzheimer's disease genetics association analysis demonstrate the empirical effectiveness of SABRE in reducing bias and improving inference.

stat.ME↗

arXiv2026

Guiding Diffusion Models with Semantically Degraded Conditions

Classifier-Free Guidance (CFG) is a cornerstone of modern text-to-image models, yet its reliance on a semantically vacuous null prompt ($\varnothing$) generates a guidance signal prone to geometric entanglement. This is a key factor limiting its precision, leading to well-documented failures in complex compositional tasks. We propose Condition-Degradation Guidance (CDG), a novel paradigm that replaces the null prompt with a strategically degraded condition, $\boldsymbol{c}_{\text{deg}}$. This reframes guidance from a coarse "good vs. null" contrast to a more refined "good vs. almost good" discrimination, thereby compelling the model to capture fine-grained semantic distinctions. We find that tokens in transformer text encoders split into two functional roles: content tokens encoding object semantics, and context-aggregating tokens capturing global context. By selectively degrading only the former, CDG constructs $\boldsymbol{c}_{\text{deg}}$ without external models or training. Validated across diverse architectures including Stable Diffusion 3, FLUX, and Qwen-Image, CDG markedly improves compositional accuracy and text-image alignment. As a lightweight, plug-and-play module, it achieves this with negligible computational overhead. Our work challenges the reliance on static, information-sparse negative samples and establishes a new principle for diffusion guidance: the construction of adaptive, semantically-aware negative samples is critical to achieving precise semantic control. Code is available at https://github.com/Ming-321/Classifier-Degradation-Guidance.

cs.CV↗

arXiv2025

Development of a dual-phase xenon time projection chamber prototype for the RELICS experiment

The RELICS (REactor neutrino LIquid xenon Coherent elastic Scattering) experiment aims to detect coherent elastic neutrino-nucleus scattering from reactor antineutrinos using a dual-phase xenon time projection chamber. To validate the detector concept and ensure technical reliability for the full-scale experiment, a dedicated prototype was designed, constructed, and operated. This work presents an overview of the design, construction, and operational performance of the prototype, with emphasis on its major subsystems, including the TPC, cryogenic and xenon purification systems, slow control, and data acquisition. During operation, the detector demonstrated the capability to achieve a sub-keV energy threshold required for the RELICS physics program, as reflected by a measured single electron gain of 34.30~$\pm$~0.01~(stat.)~PE/e$^-$ and the successful detection of 0.27~keV L-shell decay events from $^{37}$Ar. In addition, essential data analysis techniques and simulation frameworks were developed and validated, establishing the methodological foundation for future RELICS operations. The successful construction and operation of this prototype confirm the feasibility of the core technologies and provide a crucial experimental basis for the final RELICS detector.

physics.ins-det↗

arXiv2025

Design and characterization of a photosensor system for the RELICS experiment

In this paper, we present the design and characterization of a photosensor system developed for the RELICS experiment. An extended dynamic range base was designed to mitigate photomultiplier tube (PMT) saturation caused by intense cosmic muon backgrounds in the surface-level RELICS detector. The system employs dual readout from the anode and the seventh dynode to extend the linear response range of the PMT. In particular, our characterization and measurements of Hamamatsu R8520-406 PMTs confirm stable operation under positive high-voltage bias, extending the linear response range by more than an order of magnitude. Furthermore, a model of PMT saturation and recovery was developed to evaluate the influence of cosmic muon signals in the RELICS detector. The results demonstrate the system capability to detect coherent elastic neutrino-nucleus scattering signals under surface-level cosmic backgrounds, and suggest the potential to extend the scientific reach of RELICS to MeV-scale interactions.

physics.ins-det↗

arXiv2025

Optimal-PhiBE: A PDE-based Model-free framework for Continuous-time Reinforcement Learning

This paper addresses continuous-time reinforcement learning (CTRL) where the system dynamics are governed by an unknown stochastic differential equation, and only discrete-time observations are available. Existing approaches face limitations: model-based PDE methods suffer from non-identifiability, while model-free methods based on the discrete-time optimal Bellman equation (Optimal-BE) suffer from large discretization errors that are highly sensitive to both the system dynamics and the reward structure. To overcome these challenges, we introduce Optimal-PhiBE, a formulation that integrates discrete-time information into a continuous-time PDE, combining the strength of both existing frameworks while mitigating their limitations. Optimal-PhiBE exhibits smaller discretization errors when the uncontrolled system evolves slowly, and demonstrates reduced sensitivity to oscillatory reward structures, and enables model-free algorithms that bypass explicit dynamics estimation. In the linear-quadratic regulator (LQR) setting, sharp error bounds are established for both Optimal-PhiBE and Optimal-BE. The results show that Optimal-PhiBE exactly recovers the optimal policy in the undiscounted case and substantially outperforms Optimal-BE when the problem is weakly discounted or control-dominant. Furthermore, we extend Optimal-PhiBE to higher orders, providing increasingly accurate approximations. A model-free policy iteration algorithm is proposed to solve the Optimal-PhiBE directly from trajectory data. Numerical experiments are conducted to verify the theoretical findings.

math.OC↗

arXiv2025

Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank

Local learning offers an alternative to traditional end-to-end back-propagation in deep neural networks, significantly reducing GPU memory consumption. Although it has shown promise in image classification tasks, its extension to other visual tasks has been limited. This limitation arises primarily from two factors: 1) architectures designed specifically for classification are not readily adaptable to other tasks, which prevents the effective reuse of task-specific knowledge from architectures tailored to different problems; 2) these classification-focused architectures typically lack cross-scale feature communication, leading to degraded performance in tasks like object detection and super-resolution. To address these challenges, we propose the Feature Bank Augmented auxiliary network (FBA), which introduces a simplified design principle and incorporates a feature bank to enhance cross-task adaptability and communication. This work represents the first successful application of local learning methods beyond classification, demonstrating that FBA not only conserves GPU memory but also achieves performance on par with end-to-end approaches across multiple datasets for various visual tasks.

cs.CV↗

arXiv2025

Global p-Values in Multi-Design Studies

Replicability issues -- referring to the difficulty or failure of independent researchers to corroborate the results of published studies -- have hindered the meaningful progression of science and eroded public trust in scientific findings. In response to the replicability crisis, one approach is the use of multi-design studies, which incorporate multiple analysis strategies to address a single research question. However, there remains a lack of methods for effectively combining outcomes in multi-design studies. In this paper, we propose a unified framework based on the g-value, for global p-value, which enables meaningful aggregation of outcomes from all the considered analysis strategies in multi-design studies. Our framework mitigates the risk of selective reporting while rigorously controlling type I error rates. At the same time, it maintains statistical power and reduces the likelihood of overlooking true positive effects. Importantly, our method is flexible and broadly applicable across various scientific domains and outcome results.

stat.ME↗

arXiv2025

LCGC: Learning from Consistency Gradient Conflicting for Class-Imbalanced Semi-Supervised Debiasing

Classifiers often learn to be biased corresponding to the class-imbalanced dataset, especially under the semi-supervised learning (SSL) set. While previous work tries to appropriately re-balance the classifiers by subtracting a class-irrelevant image's logit, but lacks a firm theoretical basis. We theoretically analyze why exploiting a baseline image can refine pseudo-labels and prove that the black image is the best choice. We also indicated that as the training process deepens, the pseudo-labels before and after refinement become closer. Based on this observation, we propose a debiasing scheme dubbed LCGC, which Learning from Consistency Gradient Conflicting, by encouraging biased class predictions during training. We intentionally update the pseudo-labels whose gradient conflicts with the debiased logits, representing the optimization direction offered by the over-imbalanced classifier predictions. Then, we debiased the predictions by subtracting the baseline image logits during testing. Extensive experiments demonstrate that LCGC can significantly improve the prediction accuracy of existing CISSL models on public benchmarks.

cs.CV↗

arXiv2024

MLAAN: Scaling Supervised Local Learning with Multilaminar Leap Augmented Auxiliary Network

Deep neural networks (DNNs) typically employ an end-to-end (E2E) training paradigm which presents several challenges, including high GPU memory consumption, inefficiency, and difficulties in model parallelization during training. Recent research has sought to address these issues, with one promising approach being local learning. This method involves partitioning the backbone network into gradient-isolated modules and manually designing auxiliary networks to train these local modules. Existing methods often neglect the interaction of information between local modules, leading to myopic issues and a performance gap compared to E2E training. To address these limitations, we propose the Multilaminar Leap Augmented Auxiliary Network (MLAAN). Specifically, MLAAN comprises Multilaminar Local Modules (MLM) and Leap Augmented Modules (LAM). MLM captures both local and global features through independent and cascaded auxiliary networks, alleviating performance issues caused by insufficient global features. However, overly simplistic auxiliary networks can impede MLM's ability to capture global information. To address this, we further design LAM, an enhanced auxiliary network that uses the Exponential Moving Average (EMA) method to facilitate information exchange between local modules, thereby mitigating the shortsightedness resulting from inadequate interaction. The synergy between MLM and LAM has demonstrated excellent performance. Our experiments on the CIFAR-10, STL-10, SVHN, and ImageNet datasets show that MLAAN can be seamlessly integrated into existing local learning frameworks, significantly enhancing their performance and even surpassing end-to-end (E2E) training methods, while also reducing GPU memory consumption.

cs.CV↗

arXiv2024

Accurate Inference for Penalized Logistic Regression

Inference for high-dimensional logistic regression models using penalized methods has been a challenging research problem. As an illustration, a major difficulty is the significant bias of the Lasso estimator, which limits its direct application in inference. Although various bias corrected Lasso estimators have been proposed, they often still exhibit substantial biases in finite samples, undermining their inference performance. These finite sample biases become particularly problematic in one-sided inference problems, such as one-sided hypothesis testing. This paper proposes a novel two-step procedure for accurate inference in high-dimensional logistic regression models. In the first step, we propose a Lasso-based variable selection method to select a suitable submodel of moderate size for subsequent inference. In the second step, we introduce a bias corrected estimator to fit the selected submodel. We demonstrate that the resulting estimator from this two-step procedure has a small bias order and enables accurate inference. Numerical studies and an analysis of alcohol consumption data are included, where our proposed method is compared to alternative approaches. Our results indicate that the proposed method exhibits significantly smaller biases than alternative methods in finite samples, thereby leading to improved inference performance.

stat.ME↗

arXiv2024

Replacement Learning: Training Vision Tasks with Fewer Learnable Parameters

Traditional end-to-end deep learning models often enhance feature representation and overall performance by increasing the depth and complexity of the network during training. However, this approach inevitably introduces issues of parameter redundancy and resource inefficiency, especially in deeper networks. While existing works attempt to skip certain redundant layers to alleviate these problems, challenges related to poor performance, computational complexity, and inefficient memory usage remain. To address these issues, we propose an innovative training approach called Replacement Learning, which mitigates these limitations by completely replacing all the parameters of the frozen layers with only two learnable parameters. Specifically, Replacement Learning selectively freezes the parameters of certain layers, and the frozen layers utilize parameters from adjacent layers, updating them through a parameter integration mechanism controlled by two learnable parameters. This method leverages information from surrounding structures, reduces computation, conserves GPU memory, and maintains a balance between historical context and new inputs, ultimately enhancing overall model performance. We conducted experiments across four benchmark datasets, including CIFAR-10, STL-10, SVHN, and ImageNet, utilizing various architectures such as CNNs and ViTs to validate the effectiveness of Replacement Learning. Experimental results demonstrate that our approach reduces the number of parameters, training time, and memory consumption while completely surpassing the performance of end-to-end training.

cs.CV↗

arXiv2024

Inference for Large Scale Regression Models with Dependent Errors

The exponential growth in data sizes and storage costs has brought considerable challenges to the data science community, requiring solutions to run learning methods on such data. While machine learning has scaled to achieve predictive accuracy in big data settings, statistical inference and uncertainty quantification tools are still lagging. Priority scientific fields collect vast data to understand phenomena typically studied with statistical methods like regression. In this setting, regression parameter estimation can benefit from efficient computational procedures, but the main challenge lies in computing error process parameters with complex covariance structures. Identifying and estimating these structures is essential for inference and often used for uncertainty quantification in machine learning with Gaussian Processes. However, estimating these structures becomes burdensome as data scales, requiring approximations that compromise the reliability of outputs. These approximations are even more unreliable when complexities like long-range dependencies or missing data are present. This work defines and proves the statistical properties of the Generalized Method of Wavelet Moments with Exogenous variables (GMWMX), a highly scalable, stable, and statistically valid method for estimating and delivering inference for linear models using stochastic processes in the presence of data complexities like latent dependence structures and missing data. Applied examples from Earth Sciences and extensive simulations highlight the advantages of the GMWMX.

stat.ME↗

arXiv2024

LAKD-Activation Mapping Distillation Based on Local Learning

Knowledge distillation is widely applied in various fundamental vision models to enhance the performance of compact models. Existing knowledge distillation methods focus on designing different distillation targets to acquire knowledge from teacher models. However, these methods often overlook the efficient utilization of distilled information, crudely coupling different types of information, making it difficult to explain how the knowledge from the teacher network aids the student network in learning. This paper proposes a novel knowledge distillation framework, Local Attention Knowledge Distillation (LAKD), which more efficiently utilizes the distilled information from teacher networks, achieving higher interpretability and competitive performance. The framework establishes an independent interactive training mechanism through a separation-decoupling mechanism and non-directional activation mapping. LAKD decouples the teacher's features and facilitates progressive interaction training from simple to complex. Specifically, the student network is divided into local modules with independent gradients to decouple the knowledge transferred from the teacher. The non-directional activation mapping helps the student network integrate knowledge from different local modules by learning coarse-grained feature knowledge. We conducted experiments on the CIFAR-10, CIFAR-100, and ImageNet datasets, and the results show that our LAKD method significantly outperforms existing methods, consistently achieving state-of-the-art performance across different datasets.

cs.CV↗

arXiv2024

GSO-YOLO: Global Stability Optimization YOLO for Construction Site Detection

Safety issues at construction sites have long plagued the industry, posing risks to worker safety and causing economic damage due to potential hazards. With the advancement of artificial intelligence, particularly in the field of computer vision, the automation of safety monitoring on construction sites has emerged as a solution to this longstanding issue. Despite achieving impressive performance, advanced object detection methods like YOLOv8 still face challenges in handling the complex conditions found at construction sites. To solve these problems, this study presents the Global Stability Optimization YOLO (GSO-YOLO) model to address challenges in complex construction sites. The model integrates the Global Optimization Module (GOM) and Steady Capture Module (SCM) to enhance global contextual information capture and detection stability. The innovative AIoU loss function, which combines CIoU and EIoU, improves detection accuracy and efficiency. Experiments on datasets like SODA, MOCS, and CIS show that GSO-YOLO outperforms existing methods, achieving SOTA performance.

cs.CV↗

arXiv2023

Just Identified Indirect Inference Estimator: Accurate Inference through Bias Correction

An important challenge in statistical analysis lies in controlling the estimation bias when handling the ever-increasing data size and model complexity of modern data settings. In this paper, we propose a reliable estimation and inference approach for parametric models based on the Just Identified iNdirect Inference estimator (JINI). The key advantage of our approach is that it allows to construct a consistent estimator in a simple manner, while providing strong bias correction guarantees that lead to accurate inference. Our approach is particularly useful for complex parametric models, as it allows to bypass the analytical and computational difficulties (e.g., due to intractable estimating equation) typically encountered in standard procedures. The properties of JINI (including consistency, asymptotic normality, and its bias correction property) are also studied when the parameter dimension is allowed to diverge, which provide the theoretical foundation to explain the advantageous performance of JINI in increasing dimensional covariates settings. Our simulations and an alcohol consumption data analysis highlight the practical usefulness and excellent performance of JINI when data present features (e.g., misclassification, rounding) as well as in robust estimation.

stat.ME↗