Searcharxiv⌕ Search

arXiv subjects

Hui Xu

Publications and source records attributed to Hui Xu.

At least 91 records · Page 5Linked to original sources
arXiv2023

Observability and unique continuation inequalities for the Schrödinger equations with inverse-square potentials

This paper is inspired by Wang, Wang and Zhang's work [ Observability and unique continuation inequalities for the Schrödinger equation. J. Eur. Math. Soc. 21, 3513--3572 (2019)], where they present several observability and unique continuation inequalities for the free Schrödinger equation in $\mathbb{R}^{n}$. We extend all such observability and unique continuation inequalities for the Schrödinger equations on half-line with inverse-square potentials. Technically, the proofs essentially rely on the representation of the solution, a Nazarov type uncertainty principle for the Hankel transform and an interpolation inequality for functions whose Hankel transform have compact support.

math.AP↗
arXiv2023

Extremes of vector-valued processes by finite dimensional models

Finite dimensional (FD) models, i.e., deterministic functions of time/space and finite sets of random variables, are constructed for target vector-valued random processes/fields. They are required to have two properties. First, standard Monte Carlo algorithms can be used to generate their samples, referred to as FD samples. Second, under some conditions specified by several theorems, FD samples can be used to estimate distributions of extremes and other functionals of target random functions. Numerical illustrations involving two-dimensional random processes and apparent properties of random microstructures are presented to illustrate the implementation of FD models for these stochastic problems and show that they are accurate if the conditions of our theorems are satisfied.

math.PR↗
arXiv2023

Uncertainty Intervals for Prediction Errors in Time Series Forecasting

Inference for prediction errors is critical in time series forecasting pipelines. However, providing statistically meaningful uncertainty intervals for prediction errors remains relatively under-explored. Practitioners often resort to forward cross-validation (FCV) for obtaining point estimators and constructing confidence intervals based on the Central Limit Theorem (CLT). The naive version assumes independence, a condition that is usually invalid due to time correlation. These approaches lack statistical interpretations and theoretical justifications even under stationarity. This paper systematically investigates uncertainty intervals for prediction errors in time series forecasting. We first distinguish two key inferential targets: the stochastic test error over near future data points, and the expected test error as the expectation of the former. The stochastic test error is often more relevant in applications needing to quantify uncertainty over individual time series instances. To construct prediction intervals for the stochastic test error, we propose the quantile-based forward cross-validation (QFCV) method. Under an ergodicity assumption, QFCV intervals have asymptotically valid coverage and are shorter than marginal empirical quantiles. In addition, we also illustrate why naive CLT-based FCV intervals fail to provide valid uncertainty intervals, even with certain corrections. For non-stationary time series, we further provide rolling intervals by combining QFCV with adaptive conformal prediction to give time-average coverage guarantees. Overall, we advocate the use of QFCV procedures and demonstrate their coverage and efficiency through simulations and real data examples.

stat.ME↗
arXiv2023

SHAPE: A Sample-adaptive Hierarchical Prediction Network for Medication Recommendation

Effectively medication recommendation with complex multimorbidity conditions is a critical task in healthcare. Most existing works predicted medications based on longitudinal records, which assumed the information transmitted patterns of learning longitudinal sequence data are stable and intra-visit medical events are serialized. However, the following conditions may have been ignored: 1) A more compact encoder for intra-relationship in the intra-visit medical event is urgent; 2) Strategies for learning accurate representations of the variable longitudinal sequences of patients are different. In this paper, we proposed a novel Sample-adaptive Hierarchical medicAtion Prediction nEtwork, termed SHAPE, to tackle the above challenges in the medication recommendation task. Specifically, we design a compact intra-visit set encoder to encode the relationship in the medical event for obtaining visit-level representation and then develop an inter-visit longitudinal encoder to learn the patient-level longitudinal representation efficiently. To endow the model with the capability of modeling the variable visit length, we introduce a soft curriculum learning method to assign the difficulty of each sample automatically by the visit length. Extensive experiments on a benchmark dataset verify the superiority of our model compared with several state-of-the-art baselines.

cs.LG↗
arXiv2023

Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation

Temporal knowledge graphs, representing the dynamic relationships and interactions between entities over time, have been identified as a promising approach for event forecasting. However, a limitation of most temporal knowledge graph reasoning methods is their heavy reliance on the recurrence or periodicity of events, which brings challenges to inferring future events related to entities that lack historical interaction. In fact, the current state of affairs is often the result of a combination of historical information and underlying factors that are not directly observable. To this end, we investigate the limits of historical information for temporal knowledge graph extrapolation and propose a new event forecasting model called Contrastive Event Network (CENET) based on a novel training framework of historical contrastive learning. CENET learns both the historical and non-historical dependency to distinguish the most potential entities that best match the given query. Simultaneously, by launching contrastive learning, it trains representations of queries to probe whether the current moment is more dependent on historical or non-historical events. These representations further help train a binary classifier, whose output is a boolean mask, indicating the related entities in the search space. During the inference process, CENET employs a mask-based strategy to generate the final results. We evaluate our proposed model on five benchmark graphs. The results demonstrate that CENET significantly outperforms all existing methods in most metrics, achieving at least 8.3% relative improvement of Hits@1 over previous state-of-the-art baselines on event-based datasets.

cs.AI↗
arXiv2023

Is unsafe an Achilles' Heel? A Comprehensive Study of Safety Requirements in Unsafe Rust Programming

Rust is an emerging, strongly-typed programming language focusing on efficiency and memory safety. With increasing projects adopting Rust, knowing how to use Unsafe Rust is crucial for Rust security. We observed that the description of safety requirements needs to be unified in Unsafe Rust programming. Current unsafe API documents in the standard library exhibited variations, including inconsistency and insufficiency. To enhance Rust security, we suggest unsafe API documents to list systematic descriptions of safety requirements for users to follow. In this paper, we conducted the first comprehensive empirical study on safety requirements across unsafe boundaries. We studied unsafe API documents in the standard library and defined 19 safety properties (SP). We then completed the data labeling on 416 unsafe APIs while analyzing their correlation to find interpretable results. To validate the practical usability and SP coverage, we categorized existing Rust CVEs until 2023-07-08 and performed a statistical analysis of std unsafe API usage toward the crates.io ecosystem. In addition, we conducted a user survey to gain insights into four aspects from experienced Rust programmers. We finally received 50 valid responses and confirmed our classification with statistical significance.

cs.SE↗
arXiv2023

Physics-Assisted Reduced-Order Modeling for Identifying Dominant Features of Transonic Buffet

Transonic buffet is a flow instability phenomenon that arises from the interaction between the shock wave and the separated boundary layer. This flow phenomenon is considered to be highly detrimental during flight and poses a significant risk to the structural strength and fatigue life of aircraft. Up to now, there has been a lack of an accurate, efficient, and intuitive metric to predict buffet and impose a feasible constraint on aerodynamic design. In this paper, a Physics-Assisted Variational Autoencoder (PAVAE) is proposed to identify dominant features of transonic buffet, which combines unsupervised reduced-order modeling with additional physical information embedded via a buffet classifier. Specifically, four models with various weights adjusting the contribution of the classifier are trained, so as to investigate the impact of buffet information on the latent space. Statistical results reveal that buffet state can be determined exactly with just one latent space when a proper weight of classifier is chosen. The dominant latent space further reveals a strong relevance with the key flow features located in the boundary layers downstream of shock. Based on this identification, the displacement thickness at 80% chordwise location is proposed as a metric for buffet prediction. This metric achieves an accuracy of 98.5% in buffet state classification, which is more reliable than the existing separation metric used in design. The proposed method integrates the benefits of feature extraction, flow reconstruction, and buffet prediction into a unified framework, demonstrating its potential in low-dimensional representations of high-dimensional flow data and interpreting the "black box" neural network.

physics.flu-dyn↗
arXiv2022

Temporal Knowledge Graph Reasoning with Historical Contrastive Learning

Temporal knowledge graph, serving as an effective way to store and model dynamic relations, shows promising prospects in event forecasting. However, most temporal knowledge graph reasoning methods are highly dependent on the recurrence or periodicity of events, which brings challenges to inferring future events related to entities that lack historical interaction. In fact, the current moment is often the combined effect of a small part of historical information and those unobserved underlying factors. To this end, we propose a new event forecasting model called Contrastive Event Network (CENET), based on a novel training framework of historical contrastive learning. CENET learns both the historical and non-historical dependency to distinguish the most potential entities that can best match the given query. Simultaneously, it trains representations of queries to investigate whether the current moment depends more on historical or non-historical events by launching contrastive learning. The representations further help train a binary classifier whose output is a boolean mask to indicate related entities in the search space. During the inference process, CENET employs a mask-based strategy to generate the final results. We evaluate our proposed model on five benchmark graphs. The results demonstrate that CENET significantly outperforms all existing methods in most metrics, achieving at least $8.3\%$ relative improvement of Hits@1 over previous state-of-the-art baselines on event-based datasets.

cs.AI↗
arXiv2022

Segmentation, Classification, and Quality Assessment of UW-OCTA Images for the Diagnosis of Diabetic Retinopathy

Diabetic Retinopathy (DR) is a severe complication of diabetes that can cause blindness. Although effective treatments exist (notably laser) to slow the progression of the disease and prevent blindness, the best treatment remains prevention through regular check-ups (at least once a year) with an ophthalmologist. Optical Coherence Tomography Angiography (OCTA) allows for the visualization of the retinal vascularization, and the choroid at the microvascular level in great detail. This allows doctors to diagnose DR with more precision. In recent years, algorithms for DR diagnosis have emerged along with the development of deep learning and the improvement of computer hardware. However, these usually focus on retina photography. There are no current methods that can automatically analyze DR using Ultra-Wide OCTA (UW-OCTA). The Diabetic Retinopathy Analysis Challenge 2022 (DRAC22) provides a standardized UW-OCTA dataset to train and test the effectiveness of various algorithms on three tasks: lesions segmentation, quality assessment, and DR grading. In this paper, we will present our solutions for the three tasks of the DRAC22 challenge. The obtained results are promising and have allowed us to position ourselves in the TOP 5 of the segmentation task, the TOP 4 of the quality assessment task, and the TOP 3 of the DR grading task. The code is available at \url{https://github.com/Mostafa-EHD/Diabetic_Retinopathy_OCTA}.

eess.IV↗
arXiv2022

Joint nnU-Net and Radiomics Approaches for Segmentation and Prognosis of Head and Neck Cancers with PET/CT images

Automatic segmentation of head and neck cancer (HNC) tumors and lymph nodes plays a crucial role in the optimization treatment strategy and prognosis analysis. This study aims to employ nnU-Net for automatic segmentation and radiomics for recurrence-free survival (RFS) prediction using pretreatment PET/CT images in multi-center HNC cohort. A multi-center HNC dataset with 883 patients (524 patients for training, 359 for testing) was provided in HECKTOR 2022. A bounding box of the extended oropharyngeal region was retrieved for each patient with fixed size of 224 x 224 x 224 $mm^{3}$. Then 3D nnU-Net architecture was adopted to automatic segmentation of primary tumor and lymph nodes synchronously.Based on predicted segmentation, ten conventional features and 346 standardized radiomics features were extracted for each patient. Three prognostic models were constructed containing conventional and radiomics features alone, and their combinations by multivariate CoxPH modelling. The statistical harmonization method, ComBat, was explored towards reducing multicenter variations. Dice score and C-index were used as evaluation metrics for segmentation and prognosis task, respectively. For segmentation task, we achieved mean dice score around 0.701 for primary tumor and lymph nodes by 3D nnU-Net. For prognostic task, conventional and radiomics models obtained the C-index of 0.658 and 0.645 in the test set, respectively, while the combined model did not improve the prognostic performance with the C-index of 0.648.

eess.IV↗
arXiv2022

Multimodal data matters: language model pre-training over structured and unstructured electronic health records

As two important textual modalities in electronic health records (EHR), both structured data (clinical codes) and unstructured data (clinical narratives) have recently been increasingly applied to the healthcare domain. Most existing EHR-oriented studies, however, either focus on a particular modality or integrate data from different modalities in a straightforward manner, which usually treats structured and unstructured data as two independent sources of information about patient admission and ignore the intrinsic interactions between them. In fact, the two modalities are documented during the same encounter where structured data inform the documentation of unstructured data and vice versa. In this paper, we proposed a Medical Multimodal Pre-trained Language Model, named MedM-PLM, to learn enhanced EHR representations over structured and unstructured data and explore the interaction of two modalities. In MedM-PLM, two Transformer-based neural network components are firstly adopted to learn representative characteristics from each modality. A cross-modal module is then introduced to model their interactions. We pre-trained MedM-PLM on the MIMIC-III dataset and verified the effectiveness of the model on three downstream clinical tasks, i.e., medication recommendation, 30-day readmission prediction and ICD coding. Extensive experiments demonstrate the power of MedM-PLM compared with state-of-the-art methods. Further analyses and visualizations show the robustness of our model, which could potentially provide more comprehensive interpretations for clinical decision-making.

cs.CL↗
arXiv2022

KnowledgeShovel: An AI-in-the-Loop Document Annotation System for Scientific Knowledge Base Construction

Constructing a comprehensive, accurate, and useful scientific knowledge base is crucial for human researchers synthesizing scientific knowledge and for enabling Al-driven scientific discovery. However, the current process is difficult, error-prone, and laborious due to (1) the enormous amount of scientific literature available; (2) the highly-specialized scientific domains; (3) the diverse modalities of information (text, figure, table); and, (4) the silos of scientific knowledge in different publications with inconsistent formats and structures. Informed by a formative study and iterated with participatory design workshops, we designed and developed KnowledgeShovel, an Al-in-the-Loop document annotation system for researchers to construct scientific knowledge bases. The design of KnowledgeShovel introduces a multi-step multi-modal human-AI collaboration pipeline that aligns with users' existing workflows to improve data accuracy while reducing the human burden. A follow-up user evaluation with 7 geoscience researchers shows that KnowledgeShovel can enable efficient construction of scientific knowledge bases with satisfactory accuracy.

cs.DL↗
arXiv2022

Estimation of prediction error with known covariate shift

In supervised learning, the estimation of prediction error on unlabeled test data is an important task. Existing methods are usually built on the assumption that the training and test data are sampled from the same distribution, which is often violated in practice. As a result, traditional estimators like cross-validation (CV) will be biased and this may result in poor model selection. In this paper, we assume that we have a test dataset in which the feature values are available but not the outcome labels, and focus on a particular form of distributional shift called "covariate shift". We propose an alternative method based on parametric bootstrap of the target of conditional error. Empirically, our method outperforms CV for both simulation and real data example across different modeling tasks.

stat.ME↗
arXiv2022

Empirical Bayes Multistage Testing for Large-Scale Experiments

Modern application of A/B tests is challenging due to its large scale in various dimensions, which demands flexibility to deal with multiple testing sequentially. The state-of-the-art practice first reduces the observed data stream to always-valid p-values, and then chooses a cut-off as in conventional multiple testing schemes. Here we propose an alternative method called AMSET (adaptive multistage empirical Bayes test) by incorporating historical data in decision-making to achieve efficiency gains while retaining marginal false discovery rate (mFDR) control that is immune to peeking. We also show that a fully data-driven estimation in AMSET performs robustly to various simulation and real data settings at a large mobile app social network company.

stat.ME↗
arXiv2022

Iterative Adaptively Regularized LASSO-ADMM Algorithm for CFAR Estimation of Sparse Signals: IAR-LASSO-ADMM-CFAR Algorithm

The least-absolute shrinkage and selection operator (LASSO) is a regularization technique for estimating sparse signals of interest emerging in various applications and can be efficiently solved via the alternating direction method of multipliers (ADMM), which will be termed as LASSO-ADMM algorithm. The choice of the regularization parameter has significant impact on the performance of LASSO-ADMM algorithm. However, the optimization for the regularization parameter in the existing LASSO-ADMM algorithms has not been solved yet. In order to optimize this regularization parameter, we propose an efficient iterative adaptively regularized LASSO-ADMM (IAR-LASSO-ADMM) algorithm by iteratively updating the regularization parameter in the LASSO-ADMM algorithm. Moreover, a method is designed to iteratively update the regularization parameter by adding an outer iteration to the LASSO-ADMM algorithm. Specifically, at each outer iteration the zero support of the estimate obtained by the inner LASSO-ADMM algorithm is utilized to estimate the noise variance, and the noise variance is utilized to update the threshold according to a pre-defined const false alarm rate (CFAR). Then, the resulting threshold is utilized to update both the non-zero support of the estimate and the regularization parameter, and proceed to the next inner iteration. In addition, a suitable stopping criterion is designed to terminate the outer iteration process to obtain the final non-zero support of the estimate of the sparse measurement signals. The resulting algorithm is termed as IAR-LASSO-ADMM-CFAR algorithm. Finally, simulation results have been presented to show that the proposed IAR-LASSO-ADMM-CFAR algorithm outperforms the conventional LASSO-ADMM algorithm and other existing algorithms in terms of reconstruction accuracy, and its sparsity order estimate is more accurate than the existing algorithms.

cs.IT↗
arXiv2022

STELLA: Sparse Taint Analysis for Enclave Leakage Detection

Intel SGX (Software Guard Extension) is a promising TEE (trusted execution environment) technique that can protect programs running in user space from being maliciously accessed by the host operating system. Although it provides hardware access control and memory encryption, the actual effectiveness also depends on the quality of the software. In particular, improper implementation of a code snippet running inside the enclave may still leak private data due to the invalid use of pointers. This paper serves as a first attempt to study the privacy leakage issues of enclave code and proposes a novel static sparse taint analysis approach to detect them. We first summarize five common patterns of leakage code. Based on these patterns, our approach performs forward analysis to recognize all taint sinks and then employs a backward approach to detect leakages. Finally, we have conducted experiments with several open-source enclave programs and found 78 vulnerabilities previously unknown in 13 projects.

cs.CR↗
arXiv2022

The structures of higher rank lattice actions on dendrites

Let $Γ$ be a higher rank lattice acting on a nondegenerate dendrite $X$ with no infinite order points. We show that there exists a nondegenerate subdendrite $Y$ which is $Γ$-invariant and satisfies the following items: (1) There is an inverse system of finite actions $\{(Y_i, Γ):i=1,2,3,\cdots\}$ with monotone bonding maps $ϕ_i: Y_{i+1}\rightarrow Y_i$ and with each $Y_i$ being a dendrite, such that $(Y, Γ|Y)$ is topologically conjugate to the inverse limit $(\underset{\longleftarrow}{\lim}(Y_i, Γ), Γ)$. (2) The first point map $r:X\rightarrow Y$ is a factor map from $(X, Γ)$ to $(Y, Γ|Y)$; if $x\in X\setminus Y$, then $r(x)$ is an end point of $Y$ with infinite orbit; for each $y\in Y$, $r^{-1}(y)$ is contractible, that is there is a sequence $g_i\in Γ$ with ${\rm diam}(g_ir^{-1}(y))\rightarrow 0$.

math.DS↗