检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Adachi, Kazuki Yamaguchi, Shin'ya Kumagai, Atsutoshi NTT Computer and Data Science Laboratories Japan Kyoto University Japan

Real-world image recognition systems often face corrupted input images, which cause distribution shifts and degrade the performance of models. These systems often use a single prediction model in a central server and process images sent from various environments, such as cameras distributed in cities or cars. Such single models face images corrupted in heterogeneous ways in test time. Thus, they require to instantly adapt to the multiple corruptions during testing rather than being re-trained at a high cost. Test-time adaptation (TTA), which aims to adapt models without accessing the training dataset, is one of the settings that can address this problem. Existing TTA methods indeed work well on a single corruption. However, the adaptation ability is limited when multiple types of corruption occur, which is more realistic. We hypothesize this is because the distribution shift is more complicated, and the adaptation becomes more difficult in case of multiple corruptions. In fact, we experimentally found that a larger distribution gap remains after TTA. To address the distribution gap during testing, we propose a novel TTA method named Covariance-Aware Feature alignment (CAFe). We empirically show that CAFe outperforms prior TTA methods on image corruptions, including multiple types of corruptions. Copyright © 2022, The Authors. All rights reserved.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Loss factorization, weakly supervised learning and label noise robustness 33

Loss factorization, weakly supervised learning and label noi...

引用

33rd International Conference on Machine Learning, ICML 2016

作者： Patrini, Giorgio Nielsen, Frank Nock, Richard Carioni, Marcello Australian National University Australia Data61 Australia École Polytechnique France Sony Computer Science Laboratories Inc France Max Planck Institute for Mathematics in the Sciences Germany

ISBN: (纸本)9781510829008

We prove that the empirical risk of most wellknown loss functions factors into a linear term aggregating all labels with a term that is label free, and can further be expressed by sums of the same loss. This holds true even for non-smooth, non-convex losses and in any rkhs. The frrst term is a (kernel) mean operator - the focal quantity of this work - which we characterize as the sufficient statistic for the labels. The result tightens known generalization bounds and sheds new light on their interpretation. Factorization has a direct application on weakly supervised learning. In particular, we demonstrate that algorithms like sgd and proximal methods can be adapted with minimal effort to handle weak supervision, once the mean operator has been estimated. We apply this idea to learning with asymmetric noisy labels, connecting and extending prior work. Furthermore, we show that most losses enjoy a data-dependent (by the mean operator) form of noise robustness, in contrast with known negative results.

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

Brute-force attack mitigation on remote access services via software-defined perimeter

引用

Scientific reports 2025年第1期15卷 18599页

作者： Francis A Ruambo Elijah E Masanga Beston Lufyagila Abdelhamied A Ateya Ahmed A Abd El-Latif May Almousa Bassem Abd-El-Atty School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China. College of Information Communication and Technology Mbeya University of Science and Technology (MUST) P.O Box 131 Mbeya Tanzania. Research and Development Department Aifrruis Laboratories Mbeya Tanzania. EIAS Data Science Lab College of Computer and Information Sciences Prince Sultan University 11586 Riyadh Saudi Arabia. Department of Electronics and Communications Engineering Zagazig University Zagazig 44519 Sharqia Egypt. EIAS Data Science Lab College of Computer and Information Sciences Prince Sultan University 11586 Riyadh Saudi Arabia. aabdellatif@psu.edu.sa. Center of Excellence in Quantum and Intelligent Computing Prince Sultan University 11586 Riyadh Saudi Arabia. aabdellatif@psu.edu.sa. Department of Mathematics and Computer Science Faculty of Science Menoufia University Shibin Al Kawm 32511 Egypt. aabdellatif@psu.edu.sa. Information Technology Department College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia. Department of Computer Science Faculty of Computers and Information Luxor University Luxor 85957 Egypt. bassem.abdelatty@fci.luxor.edu.eg.

Remote Access Services (RAS)-including protocols such as Remote Desktop Protocol (RDP), Secure Shell (SSH), Virtual Network Computing (VNC), Telnet, File Transfer Protocol (FTP), and Secure File Transfer Protocol (SFTP)-are essential to modern network infrastructures, particularly with the rise of remote work and cloud adoption. However, their exposure significantly increases the risk of brute-force attacks (BFA), where adversaries systematically guess credentials to gain unauthorized access. Traditional defenses like IP blocklisting and multifactor authentication (MFA) often struggle with scalability and adaptability to distributed attacks. This study introduces a zero-trust-aligned Software-Defined Perimeter (SDP) architecture that integrates Single Packet Authorization (SPA) for service cloaking and Connection Tracking (ConnTrack) for real-time session analysis. A Docker-based prototype was developed and tested, demonstrating no successful BFA attempts observed, latency reduction by above 10% across all evaluated RAS protocols, and the system CPU utilization reduction by 48.7% under attack conditions without impacting normal throughput. It also proved effective against connection-oriented attacks, including port scanning and distributed denial of service (DDoS) attacks. The proposed architecture offers a scalable and efficient security framework by embedding proactive defense at the authentication layer. This work advances zero-trust implementations and delivers practical, low-overhead protection for securing RAS against evolving cyber threats.

关键词： Brute-force attacks Remote access services (RAS) Single packet authorization (SPA) Software-defined perimeter (SDP) Zero-trust architecture

来源：评论

学校读者我要写书评

暂无评论

Improving Raft Performance with Bulk Transfers

Improving Raft Performance with Bulk Transfers

引用

International Symposium on Computing and Networking Workshops (CANDARW)

作者： Aoi Yamashita Masahiro Tanaka Yutaro Bessho Yasuhiro Fujiwara Hideyuki Kawashima Graduate School of Keio University NTT Computer and Data Science Laboratories NTT Communication Science Laboratories Keio University

Raft is known as a replicating state machine that tolerates crash faults, and its use enables various distributed systems, including distributed transaction processing systems. The original Raft protocol creates an intra-cluster consensus by having the leader generate a log of each incoming client request and replicate it to its followers. When requests arrive frequently, the number of replications increases, increasing the number of communications and possibly leading to performance degradation. To solve this problem, we propose a bulk-transfer protocol that replicates multiple requests at once. We implemented the Raft system to verify the effect of the proposed method. We measured the performance of the implemented system when multiple requests were transferred in bulk and observed an increase in throughput with an increase in the amount of data replicated at a time. The highest throughput of 214 MB/sec was achieved when replicating 12.5 MB at a time. This is 12,066 times higher than the performance when replicating one request (18 B) at a time. Besides, the size of the log is reduced to 5/9 of the conventional method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edit and Alphabet-Ordering Sensitivity of Lex-Parse 49

Edit and Alphabet-Ordering Sensitivity of Lex-Parse

引用

49th International Symposium on Mathematical Foundations of computer science, MFCS 2024

作者： Nakashima, Yuto Köppl, Dominik Funakoshi, Mitsuru Inenaga, Shunsuke Bannai, Hideo Department of Informatics Kyushu University Fukuoka Japan Department of Computer Science and Engineering University of Yamanashi Kofu Japan M&D Data Science Center Tokyo Medical and Dental University Japan NTT Communication Science Laboratories Kyoto Japan

ISBN: (纸本)9783959773355

We investigate the compression sensitivity [Akagi et al., 2023] of lex-parse [Navarro et al., 2021] for two operations: (1) single character edit and (2) modification of the alphabet ordering, and give tight upper and lower bounds for both operations (i.e., we show Θ(log n) bounds for strings of length n). For both lower bounds, we use the family of Fibonacci words. For the bounds on edit operations, our analysis makes heavy use of properties of the Lyndon factorization of Fibonacci words to characterize the structure of lex-parse. © Yuto Nakashima, Dominik Köppl, Mitsuru Funakoshi, Shunsuke Inenaga, and Hideo Bannai.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Trilinos: Enabling Scientific Computing Across Diverse Hardware Architectures at Scale

arXiv

引用

arXiv 2025年

作者： Mayr, Matthias Heinlein, Alexander Glusa, Christian Rajamanickam, Sivasankaran Arnst, Maarten Bartlett, Roscoe A. Berger-Vergiat, Luc Boman, Erik G. Devine, Karen Harper, Graham Heroux, Michael Hoemmen, Mark Hu, Jonathan Kelley, Brian Kim, Kyungjoo Kouri, Drew P. Kuberry, Paul Liegeois, Kim Ober, Curtis C. Pawlowski, Roger Pearson, Carl Perego, Mauro Phipps, Eric Ridzal, Denis Roberts, Nathan V. Siefert, Christopher M. Thornquist, Heidi K. Tomasetti, Romin Trott, Christian R. Tuminaro, Raymond S. Willenbring, James M. Wolf, Michael M. Yamazaki, Ichitaro Data Science & Computing Lab Institute for Mathematics and Computer-Based Simulation Universität der Bundeswehr München Werner-Heisenberg-Weg 39 Neubiberg85577 Germany Delft University of Technology Mekelweg 4 Delft2628CD Netherlands Sandia National Laboratories 1515 Eubank Blvd SE AlbuquerqueNM87123 United States University of Liege Quartier Polytech 1 allée de la Découverte 9 Liege4000 Belgium ParaTools Inc. 18125 Kreigle Lake Road AvonMN56310 United States NVIDIA 2788 San Tomas Expressway Santa ClaraCA95051 United States Advanced Micro Devices Inc. 2485 Augustine Dr Santa ClaraCA95054 United States

Trilinos is a community-developed, open-source software framework that facilitates building large-scale, complex, multiscale, multiphysics simulation code bases for scientific and engineering problems. Since the Trilinos framework has undergone substantial changes to support new applications and new hardware architectures, this document is an update to "An Overview of the Trilinos project" by Heroux et al. (ACM Transactions on Mathematical Software, 31(3):397–423, 2005). It describes the design of Trilinos, introduces its new organization in product areas, and highlights established and new features available in Trilinos. Particular focus is put on the modernized software stack based on the Kokkos ecosystem to deliver performance portability across heterogeneous hardware architectures. This paper also outlines the organization of the Trilinos community and the contribution model to help onboard interested users and *** Codes 65-04, 65Y05 Copyright © 2025, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Pruning randomly initialized neural networks with iterative randomization 21

Pruning randomly initialized neural networks with iterative ...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Daiki Chijiwa Shin'ya Yamaguchi Yasutoshi Ida Kenji Umakoshi Tomohiro Inoue NTT Computer and Data Science Laboratories NTT Corporation NTT Social Informatics Laboratories NTT Corporation

ISBN: (纸本)9781713845393

Pruning the weights of randomly initialized neural networks plays an important role in the context of lottery ticket hypothesis. Ramanujan et al. [23] empirically showed that only pruning the weights can achieve remarkable performance instead of optimizing the weight values. However, to achieve the same level of performance as the weight optimization, the pruning approach requires more parameters in the networks before pruning and thus more memory space. To overcome this parameter inefficiency, we introduce a novel framework to prune randomly initialized neural networks with iteratively randomizing weight values (IteRand). Theoretically, we prove an approximation theorem in our framework, which indicates that the randomizing operations are provably effective to reduce the required number of the parameters. We also empirically demonstrate the parameter efficiency in multiple experiments on CIFAR-10 and ImageNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Algorithm for K-Multiple-Means

引用

Proceedings of the ACM on Management of data 2024年第1期2卷 1-26页

作者： Yasuhiro Fujiwara Atsutoshi Kumagai Yasutoshi Ida Masahiro Nakano Makoto Nakatsuji Akisato Kimura NTT Communication Science Laboratories Atsugi-shi Kanagawa Japan NTT Computer and Data Science Laboratories Musashino-shi Tokyo Japan NTT Human Informatics Laboratories Yokosuka-shi Kanagawa Japan

K-Multiple-Means is an extension of K-means for the clustering of multiple means used in many applications, such as image segmentation, load balancing, and blind-source separation. Since K-means uses only one mean to represent each cluster, it fails to capture non-spherical cluster structures of data points. However, since K-Multiple-Means represents the cluster by computing multiple means and grouping them into specified c clusters, it can effectively capture the non-spherical clusters of the data points. To obtain the clusters, K-Multiple-Means updates a similarity matrix of a bipartite graph between the data points and the multiple means by iteratively computing the leading c singular vectors of the matrix. K-Multiple-Means, however, incurs a high computation cost for large-scale data due to the iterative SVD computations. Our proposal, F-KMM, increases the efficiency of K-Multiple-Means by computing the singular vectors from a smaller similarity matrix between the multiple means obtained from the similarity matrix of the bipartite graph. To compute the similarity matrix of the bipartite graph efficiently, we skip unnecessary distance computations and estimate lower bounding distances between the data points and the multiple means. Theoretically, the proposed approach guarantees the same clustering results as K-Multiple-Means since it can exactly compute the singular vectors from the similarity matrix between the multiple means. Experiments show that our approach is several orders of magnitude faster than previous clustering approaches that use multiple means.

关键词： algorithm clustering efficient

来源：评论

学校读者我要写书评

暂无评论

Learning maximal ancestral graphs with robustness for faithfulness violations 2nd

Learning maximal ancestral graphs with robustness for faithf...

引用

2nd International Workshop on Advanced Methodologies for Bayesian Networks, AMBN 2015

作者： Isozaki, Takashi Kuroki, Manabu Sony Computer Science Laboratories Inc 3-14-13 Higashigotanda Shinagawa Tokyo141-0022 Japan Department of Data Science The Institute of Statistical Mathematics 10-3 Midori-cho Tachikawa Tokyo190-8562 Japan

ISBN: (纸本)9783319283784

Discovering causal models hidden in the background of observational data has been a difficult issue. It is often necessary to deal with latent common causes and selection bias for constructing causal models in real data. Ancestral graph models are effective and useful for representing causal models with latent variables. The causal faithfulness condition, which is usually assumed for determining the models, is statistically known to often be weakly violated for finite data. One of the authors developed a constraint-based causal learning algorithm that is robust against the violations while assuming no latent variables. In this study, we applied and extended the thoughts of the algorithm to the inference of ancestral graphs. The practical validity and effectiveness of the algorithm are also confirmed by using some standard datasets in comparison with FCI and RFCI algorithms. © Springer International Publishing Switzerland 2015.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Bigger is not always better: The importance of human-scale language modeling for psycholinguistics

引用

Journal of Memory and Language 2025年 144卷

作者： Ethan Gotlieb Wilcox Michael Y. Hu Aaron Mueller Alex Warstadt Leshem Choshen Chengxu Zhuang Adina Williams Ryan Cotterell Tal Linzen Department of Linguistics Georgetown University 1421 37th St NW Washington DC 20007 USA Department of Linguistics and Center for Data Science New York University 10 Washington Place NewYork NY 10003 USA Khoury College of Computer Sciences Northeastern University 440 Huntington Avenue Boston MA 02115 USA Department of Computer Science ETH Zürich Universitätstrasse 6 8092 Zürich Switzerland Electrical Engineering and Computer Science Department Massachusetts Institute of Technology 77 Massachusetts Avenue Cambridge MA 02139 USA FAIR Laboratories Meta Platforms Inc. 390 9th Ave NewYork NY 10001 USA

When trained to place high probability on a training corpus, neural network language models can learn a surprising amount about language. Recent work has demonstrated that large performance improvements can arise from simply increasing, i.e., scaling, the size of the corpora they are trained on and the number of parameters in those models. Accordingly, many contemporary systems are trained on trillions of words. While largely beneficial to performance on language applications, scaling has several downsides for both computational psycholinguistics and natural language processing research. We discuss the scientific challenges presented by the scaling paradigm, as well as the benefits that would result from language models that can learn from human-scale data. In the second half of this paper, we report on findings from a recent effort to bring about human-scale language model pretraining: the first iteration of the BabyLM Challenge, a shared task organized by the authors that invited participants to train a language model on 100 million words or less. The challenge produced several concrete best practices for practitioners interested in small-scale language modeling. For cognitive scientists, the challenge demonstrated that robust linguistic generalizations can be learned by models trained on a human-scale dataset, though this is not yet achieved through cognitively plausible mechanisms. Furthermore, it established a population of “BabyLMs” that are all effective at data-efficient language learning. Studying such models can help us identify hypotheses for the computational mechanisms that underlie human language acquisition.

关键词： Language modeling Scaling Cognitive modeling Connectionist networks Psycholinguistics Language acquisition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：