Results of simulation studies evaluating the performance of statistical methods are often considered actionable and thus can have a major impact on the way empirical research is implemented. However, so far there is limited evidence about the reproducibility and replicability of statistical simulation studies. Therefore, eight highly cited statistical simulation studies were selected, and their replicability was assessed by teams of replicators with formal training in quantitative methodology. The teams found relevant information in the original publications and used it to write simulation code with the aim of replicating the results. The primary outcome was the feasibility of replicability based on reported information in the original publications. Replicability varied greatly: Some original studies provided detailed information leading to almost perfect replication of results, whereas other studies did not provide enough information to implement any of the reported simulations. Replicators had to make choices regarding missing or ambiguous information in the original studies, error handling, and software environment. Factors facilitating replication included public availability of code, and descriptions of the data-generating procedure and methods in graphs, formulas, structured text, and publicly accessible additional resources such as technical reports. Replicability of statistical simulation studies was mainly impeded by lack of information and sustainability of information sources. Reproducibility could be achieved for simulation studies by providing open code and data as a supplement to the publication. Additionally, simulation studies should be transparently reported with all relevant information either in the research paper itself or in easily accessible supplementary material to allow for replicability.
相關內容
The computation of approximating e^tA B, where A is a large sparse matrix and B is a rectangular matrix, serves as a crucial element in numerous scientific and engineering calculations. A powerful way to consider this problem is to use Krylov subspace methods. The purpose of this work is to approximate the matrix exponential and some Cauchy-Stieltjes functions on a block vectors B of R^n*p using a rational block Lanczos algorithm. We also derive some error estimates and error bound for the convergence of the rational approximation and finally numerical results attest to the computational efficiency of the proposed method.
Code datasets are of immense value for training neural-network-based code completion models, where companies or organizations have made substantial investments to establish and process these datasets. Unluckily, these datasets, either built for proprietary or public usage, face the high risk of unauthorized exploits, resulting from data leakages, license violations, etc. Even worse, the ``black-box'' nature of neural models sets a high barrier for externals to audit their training datasets, which further connives these unauthorized usages. Currently, watermarking methods have been proposed to prohibit inappropriate usage of image and natural language datasets. However, due to domain specificity, they are not directly applicable to code datasets, leaving the copyright protection of this emerging and important field of code data still exposed to threats. To fill this gap, we propose a method, named CodeMark, to embed user-defined imperceptible watermarks into code datasets to trace their usage in training neural code completion models. CodeMark is based on adaptive semantic-preserving transformations, which preserve the exact functionality of the code data and keep the changes covert against rule-breakers. We implement CodeMark in a toolkit and conduct an extensive evaluation of code completion models. CodeMark is validated to fulfill all desired properties of practical watermarks, including harmlessness to model accuracy, verifiability, robustness, and imperceptibility.
Segmentation and spatial alignment of ultrasound (US) imaging data acquired in the in first trimester are crucial for monitoring human embryonic growth and development throughout this crucial period of life. Current approaches are either manual or semi-automatic and are therefore very time-consuming and prone to errors. To automate these tasks, we propose a multi-atlas framework for automatic segmentation and spatial alignment of the embryo using deep learning with minimal supervision. Our framework learns to register the embryo to an atlas, which consists of the US images acquired at a range of gestational age (GA), segmented and spatially aligned to a predefined standard orientation. From this, we can derive the segmentation of the embryo and put the embryo in standard orientation. US images acquired at 8+0 till 12+6 weeks GA were used and eight subjects were selected as atlas. We evaluated different fusion strategies to incorporate multiple atlases: 1) training the framework using atlas images from a single subject, 2) training the framework with data of all available atlases and 3) ensembling of the frameworks trained per subject. To evaluate the performance, we calculated the Dice score over the test set. We found that training the framework using all available atlases outperformed ensembling and gave similar results compared to the best of all frameworks trained on a single subject. Furthermore, we found that selecting images from the four atlases closest in GA out of all available atlases, regardless of the individual quality, gave the best results with a median Dice score of 0.72. We conclude that our framework can accurately segment and spatially align the embryo in first trimester 3D US images and is robust for the variation in quality that existed in the available atlases.
Recent approaches have attempted to personalize dialogue systems by leveraging profile information into models. However, this knowledge is scarce and difficult to obtain, which makes the extraction/generation of profile information from dialogues a fundamental asset. To surpass this limitation, we introduce the Profile Generation Task (PGTask). We contribute with a new dataset for this problem, comprising profile sentences aligned with related utterances, extracted from a corpus of dialogues. Furthermore, using state-of-the-art methods, we provide a benchmark for profile generation on this novel dataset. Our experiments disclose the challenges of profile generation, and we hope that this introduces a new research direction.
We study the problem of estimating the derivatives of a regression function, which has a wide range of applications as a key nonparametric functional of unknown functions. Standard analysis may be tailored to specific derivative orders, and parameter tuning remains a daunting challenge particularly for high-order derivatives. In this article, we propose a simple plug-in kernel ridge regression (KRR) estimator in nonparametric regression with random design that is broadly applicable for multi-dimensional support and arbitrary mixed-partial derivatives. We provide a non-asymptotic analysis to study the behavior of the proposed estimator in a unified manner that encompasses the regression function and its derivatives, leading to two error bounds for a general class of kernels under the strong $L_\infty$ norm. In a concrete example specialized to kernels with polynomially decaying eigenvalues, the proposed estimator recovers the minimax optimal rate up to a logarithmic factor for estimating derivatives of functions in H\"older and Sobolev classes. Interestingly, the proposed estimator achieves the optimal rate of convergence with the same choice of tuning parameter for any order of derivatives. Hence, the proposed estimator enjoys a \textit{plug-in property} for derivatives in that it automatically adapts to the order of derivatives to be estimated, enabling easy tuning in practice. Our simulation studies show favorable finite sample performance of the proposed method relative to several existing methods and corroborate the theoretical findings on its minimax optimality.
Activation functions are the linchpins of deep learning, profoundly influencing both the representational capacity and training dynamics of neural networks. They shape not only the nature of representations but also optimize convergence rates and enhance generalization potential. Appreciating this critical role, we present the Linear Oscillation (LoC) activation function, defined as $f(x) = x \times \sin(\alpha x + \beta)$. Distinct from conventional activation functions which primarily introduce non-linearity, LoC seamlessly blends linear trajectories with oscillatory deviations. The nomenclature ``Linear Oscillation'' is a nod to its unique attribute of infusing linear activations with harmonious oscillations, capturing the essence of the 'Importance of Confusion'. This concept of ``controlled confusion'' within network activations is posited to foster more robust learning, particularly in contexts that necessitate discerning subtle patterns. Our empirical studies reveal that, when integrated into diverse neural architectures, the LoC activation function consistently outperforms established counterparts like ReLU and Sigmoid. The stellar performance exhibited by the avant-garde Vision Transformer model using LoC further validates its efficacy. This study illuminates the remarkable benefits of the LoC over other prominent activation functions. It champions the notion that intermittently introducing deliberate complexity or ``confusion'' during training can spur more profound and nuanced learning. This accentuates the pivotal role of judiciously selected activation functions in shaping the future of neural network training.
Fixed-Point Algorithms for Solving the Critical Value and Upper Tail Quantile of Kuiper's Statistics
Kuiper's statistic is a good measure for the difference of ideal distribution and empirical distribution in the goodness-of-fit test. However, it is a challenging problem to solve the critical value and upper tail quantile, or simply Kuiper pair, of Kuiper's statistics due to the difficulties of solving the nonlinear equation and reasonable approximation of infinite series. The pioneering work by Kuiper just provided the key ideas and few numerical tables created from the upper tail probability $\alpha$ and sample capacity $n$, which limited its propagation and possible applications in various fields since there are infinite configurations for the parameters $\alpha$ and $n$. In this work, the contributions lie in two perspectives: firstly, the second order approximation for the infinite series of the cumulative distribution of the critical value is used to achieve higher precision; secondly, the principles and fixed-point algorithms for solving the Kuiper pair are presented with details. The algorithms are verified and validated by comparing with the table provided by Kuiper. The methods and algorithms proposed are enlightening and worthy of introducing to the college students, computer programmers, engineers, experimental psychologists and so on.
One-class classification (OCC) is a longstanding method for anomaly detection. With the powerful representation capability of the pre-trained backbone, OCC methods have witnessed significant performance improvements. Typically, most of these OCC methods employ transfer learning to enhance the discriminative nature of the pre-trained backbone's features, thus achieving remarkable efficacy. While most current approaches emphasize feature transfer strategies, we argue that the optimization objective space within OCC methods could also be an underlying critical factor influencing performance. In this work, we conducted a thorough investigation into the optimization objective of OCC. Through rigorous theoretical analysis and derivation, we unveil a key insights: any space with the suitable norm can serve as an equivalent substitute for the hypersphere center, without relying on the distribution assumption of training samples. Further, we provide guidelines for determining the feasible domain of norms for the OCC optimization objective. This novel insight sparks a simple and data-agnostic deep one-class classification method. Our method is straightforward, with a single 1x1 convolutional layer as a trainable projector and any space with suitable norm as the optimization objective. Extensive experiments validate the reliability and efficacy of our findings and the corresponding methodology, resulting in state-of-the-art performance in both one-class classification and industrial vision anomaly detection and segmentation tasks.
In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP), experiencing a rapid spread and wide adoption within recent years. Given the increasing amount of research work in this area, several KG-related approaches have been surveyed in the NLP research community. However, a comprehensive study that categorizes established topics and reviews the maturity of individual research streams remains absent to this day. Contributing to closing this gap, we systematically analyzed 507 papers from the literature on KGs in NLP. Our survey encompasses a multifaceted review of tasks, research types, and contributions. As a result, we present a structured overview of the research landscape, provide a taxonomy of tasks, summarize our findings, and highlight directions for future work.
Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to improve the cross-domain robustness of object detection. We tackle the domain shift on two levels: 1) the image-level shift, such as image style, illumination, etc, and 2) the instance-level shift, such as object appearance, size, etc. We build our approach based on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy. The two domain adaptation components are based on H-divergence theory, and are implemented by learning a domain classifier in adversarial training manner. The domain classifiers on different levels are further reinforced with a consistency regularization to learn a domain-invariant region proposal network (RPN) in the Faster R-CNN model. We evaluate our newly proposed approach using multiple datasets including Cityscapes, KITTI, SIM10K, etc. The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191