检索结果-内蒙古大学图书馆

Exponential quantum advantages for practical non-Hermitian eigenproblems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Xiao-Ming Zhang, Yukun He, Wenhao Yuan, Xiao School of Physics South China Normal University Guangzhou510006 China Center on Frontiers of Computing Studies School of Computer Science Peking University Beijing100871 China Center for Computational Science and Engineering Massachusetts Institute of Technology CambridgeMA02139 United States School of Physics Peking University Beijing100871 China

While non-Hermitian physics has attracted considerable attention, current studies are limited to small or classically solvable systems. Quantum computing, as a powerful eigensolver, have predominantly been applied to Hermitian domain, leaving their potential for studying non-Hermitian problems largely unexplored. We extend the power of quantum computing to general non-Hermitian eigenproblems. Our approach works for finding eigenvalues without extra constrains, or eigenvalues closest to specified points or lines, thus extending results for ground energy and energy gap problems for Hermitian matrices. Our algorithms have broad applications, and as examples, we consider two central problems in non-Hermitian physics. Firstly, our approach is the first to offer an efficient quantum solution to the witness of spontaneous PT-symmetry breaking, and provide provable, exponential quantum advantage. Secondly, our approach enables the estimation of Liouvillian gap, which is crucial for characterizing relaxation times. Our general approach can also find applications in many other areas, such as the study of Markovian stochastic processes. These results underscore the significance of our quantum algorithms for addressing practical eigenproblems across various disciplines. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

Schema-Driven Information Extraction from Heterogeneous Tables

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bai, Fan Kang, Junmo Stanovsky, Gabriel Freitag, Dayne Dredze, Mark Ritter, Alan College of Computing Georgia Institute of Technology United States School of Computer Science and Engineering The Hebrew University of Jerusalem Artificial Intelligence Center SRI International United States Department of Computer Science Johns Hopkins University United States

In this paper, we explore the question of whether large language models can support cost-efficient information extraction from tables. We introduce schema-driven information extraction, a new task that transforms tabular data into structured records following a human-authored schema. To assess various LLM’s capabilities on this task, we present a benchmark comprised of tables from four diverse domains: machine learning papers, chemistry literature, material science journals, and webpages. We use this collection of annotated tables to evaluate the ability of open-source and API-based language models to extract information from tables covering diverse domains and data formats. Our experiments demonstrate that surprisingly competitive performance can be achieved without requiring task-specific pipelines or labels, achieving F1 scores ranging from 74.2 to 96.1, while maintaining cost efficiency. Moreover, through detailed ablation studies and analyses, we investigate the factors contributing to model success and validate the practicality of distilling compact models to reduce API reliance.1 © 2023, CC BY.

关键词： Data mining

Efficient or Powerful? Trade-offs Between Machine Learning and Deep Learning for Mental Illness Detection on Social Media

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ding, Zhanyi Wang, Zhongyan Zhang, Yeyubei Cao, Yuchen Liu, Yunchong Shen, Xiaorui Tian, Yexin Dai, Jianglai University of Pennsylvania School of Engineering and Applied Science United States New York University Center for Data Science United States Georgia Institute of Technology College of Computing United States University of California Berkeley Department of EECS United States Northeastern University Khoury College of Computer Science United States

Social media platforms provide valuable insights into mental health trends by capturing user-generated discussions on conditions such as depression, anxiety, and suicidal ideation. Machine learning (ML) and deep learning (DL) models have been increasingly applied to classify mental health conditions from textual data, but selecting the most effective model involves trade-offs in accuracy, interpretability, and computational efficiency. This study evaluates multiple ML models, including logistic regression, random forest, and LightGBM, alongside deep learning architectures such as ALBERT and Gated Recurrent Units (GRUs), for both binary and multi-class classification of mental health conditions. Our findings indicate that ML and DL models achieve comparable classification performance on medium-sized datasets, with ML models offering greater interpretability through variable importance scores, while DL models are more robust to complex linguistic patterns. Additionally, ML models require explicit feature engineering, whereas DL models learn hierarchical representations directly from text. Logistic regression provides the advantage of capturing both positive and negative associations between features and mental health conditions, whereas tree-based models prioritize decision-making power through split-based feature selection. This study offers empirical insights into the advantages and limitations of different modeling approaches and provides recommendations for selecting appropriate methods based on dataset size, interpretability needs, and computational constraints. © 2025, CC BY.

关键词： Contrastive Learning

Unlocking the Boundaries of Thought: A Reasoning Granularity Framework to Quantify and Optimize Chain-of-Thought

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Qiguang Qin, Libo Wang, Jiaqi Zhou, Jinxuan Che, Wanxiang Research Center for Social Computing and Information Retrieval China Harbin Institute of Technology China School of Computer Science and Engineering Central South University China The Chinese University of Hong Kong Hong Kong

Chain-of-Thought (CoT) reasoning has emerged as a promising approach for enhancing the performance of large language models (LLMs) on complex reasoning tasks. Recently, a series of studies attempt to explain the mechanisms underlying CoT, aiming to deepen the understanding of its efficacy. Nevertheless, the existing research faces two major challenges: (1) a lack of quantitative metrics to assess CoT capabilities and (2) a dearth of guidance on optimizing CoT performance. Motivated by this, in this work, we introduce a novel reasoning granularity framework (RGF) to address these challenges. To solve the lack of quantification, we first define a reasoning granularity (RG) to quantify the upper bound of CoT and establish a combination law for RG, enabling a practical quantitative approach applicable to various real-world CoT tasks. To address the lack of optimization, we propose three categories of RGs. We further optimize these categories with combination laws focused on RG promotion and reasoning path optimization for CoT improvement. Through extensive experiments on 25 models and 4 tasks, the study validates the existence and rationality of the proposed framework. Furthermore, it explains the effectiveness of 10 CoT strategies and guides optimization from two perspectives. We hope this work can provide a comprehensive understanding of the boundaries and optimization strategies for reasoning in LLMs. Our code and data are available at https://***/LightChen233/reasoning-granularity. © 2024, CC BY-SA.

关键词：

Tutorial on Using Machine Learning and Deep Learning Models for Mental Illness Detection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Yeyubei Wang, Zhongyan Ding, Zhanyi Tian, Yexin Dai, Jianglai Shen, Xiaorui Liu, Yunchong Cao, Yuchen University of Pennsylvania School of Engineering and Applied Science United States New York University Center for Data Science United States Georgia Institute of Technology College of Computing United States University of California Department of EECS Berkeley United States Northeastern University Khoury College of Computer Science United States

Social media has become an important source for understanding mental health, providing researchers a way to detect conditions like depression from user-generated posts. This tutorial provides practical guidance to address common challenges in applying machine learning and deep learning methods for mental health detection on these platforms. It focuses on strategies for working with diverse datasets, improving text preprocessing, and addressing issues such as imbalanced data and model evaluation. Real-world examples and step-by-step instructions demonstrate how to apply these techniques effectively, with an emphasis on transparency, reproducibility, and ethical considerations. By sharing these approaches, this tutorial aims to help researchers build more reliable and widely applicable models for mental health research, contributing to better tools for early detection and intervention. © 2025, CC BY.

关键词： Adversarial machine learning

Dynamic Clustering-based Task Orchestrator in Mobile Edge computing

学校读者我要写书评

暂无评论

Dynamic Clustering-based Task Orchestrator in Mobile Edge Co...

International Wireless Communications and Mobile computing Conference, IWCMC

作者： Mona Alghamdi Atm Alam Arumugam Nallanathan Asma Cherif School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Department of Information Technology Faculty of Computing and Information Technology Center of Excellence in Smart Environment Research King AbdulAziz University Saudi Arabia

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

Multi-access Edge computing (MEC) is an emerging paradigm designed to provide storage, computing and communication capabilities in the proximity of end-user devices. This approach facilitates the deployment of real-time on mobile devices with limited capabilities. To realize the MEC goals, it is essential to effectively manage and offload computing tasks to both edge and cloud-based resources. However, the dynamic nature, uncertainty and mobility within edge computing environments pose significant challenges to resource management. Furthermore, the inherent software and hardware heterogeneity, coupled with the distributed nature of architecture, complicates the development of efficient task offloading strategies that can adeptly manage resources across both edge and cloud platforms. In this paper, we propose a cluster-based task edge orchestrator, where edge servers are grouped based on service demands, resource ability and other factors to improve the overall service. Our proposed method leverages the K-Medoids clustering algorithm to dynamically form clusters of suitable edge servers for offloading computing tasks with minimum response time. To validate our proposed solution, we have orchestrated a comprehensive series of tests using EdgeCloudSim. Results show that our approach outperforms its competitor in terms of average service time by around 8 %.

关键词： Wireless communication Wide area networks Multi-access edge computing Uncertainty Sensitivity Software Servers

Exponential speedups for quantum walks in random hierarchical graphs

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Balasubramanian, Shankar Li, Tongyang Harrow, Aram W. Center for Theoretical Physics Massachusetts Institute of Technology CambridgeMA02139 United States Center on Frontiers of Computing Studies School of Computer Science Peking University Beijing100871 China

There are few known exponential speedups for quantum algorithms and these tend to fall into even fewer families. One speedup that has mostly resisted generalization is the use of quantum walks to traverse the welded-tree graph, due to Childs, Cleve, Deotto, Farhi, Gutmann, and Spielman. We show how to generalize this to a large class of hierarchical graphs in which the vertices are grouped into "supervertices" which are arranged according to a d-dimensional lattice. Supervertices can have different sizes, and edges between supervertices correspond to random connections between their constituent vertices. The hitting times of quantum walks on these graphs are related to the localization properties of zero modes in certain disordered tight binding Hamiltonians. The speedups range from superpolynomial to exponential, depending on the underlying dimension and the random graph model. We also provide concrete realizations of these hierarchical graphs, and introduce a general method for constructing graphs with efficient quantum traversal times using graph sparsification. Copyright © 2023, The Authors. All rights reserved.

关键词： Hamiltonians

An Efficient and Privacy-Preserving Load Monitoring and Billing Scheme in Smart Grid

学校读者我要写书评

暂无评论

An Efficient and Privacy-Preserving Load Monitoring and Bill...

IEEE International Conference on Data science in Cyberspace (DSC)

作者： Yong Ding Enchang Yuan Changsong Yang Hai Liang Huiyong Wang Xinyong Peng Laboratory of Cryptography and Information Security School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Digital Infrastructure Guangxi Zhuang Autonomous Region Information Center Nanning China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

The smart grid is widely recognized as a highly efficient solution for mitigating carbon emissions and addressing energy crises. Within this framework, the collection of metering data from users is crucial for improving energy efficiency. However, the frequent collection of real-time metering data presents substantial challenges in terms of data privacy and communication overhead. In this paper, we propose an efficient and secure scheme that enables the system operator to monitor load and compute bills while preserving the users’ privacy. During the load monitoring phase, our scheme uses certificateless ring signatures and unique random identifiers to ensure the security of electricity data. Additionally, the proposed scheme uses improved function encryption for electricity data in a ciphertext state to protect users’ privacy during dynamic billing. Detailed security analysis demonstrates that our scheme meets the security requirements of the smart grid. Furthermore, we compare our scheme with existing schemes to demonstrate the effectiveness of our proposed scheme in terms of low computational complexity and communication overhead.

关键词： Data privacy Load monitoring Privacy Electricity Data science Real-time systems Energy efficiency Smart grids Encryption Computational complexity

FedLRDP: Federated Learning Framework with Local Random Differential Privacy

学校读者我要写书评

暂无评论

FedLRDP: Federated Learning Framework with Local Random Diff...

International Joint Conference on Neural Networks (IJCNN)

作者： Runtian Zhou Anming Dong Jiguo Yu Qingyan Ding Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Big Data Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Federated learning (FL) is a distributed machine learning framework enabling multiple clients to collaboratively train a shared ML model without sharing raw data. Despite its aim to safeguard data security and privacy, FL faces risks from advanced adversarial attacks like membership inference attack (MIA), potentially leaking sensitive information. To counter these threats, differential privacy (DP) methods add noise to shared model parameters. However, traditional DP methods struggle with balancing model accuracy, training efficiency, and privacy protection, often compromising one for the other. Additionally, uniform DP mechanisms may not cater to varying client privacy and performance needs. To tackle these challenges, we propose a federated learning framework based on localized random differential privacy (FedLRDP). This approach empowers each client to control noise levels based on their privacy requirements, enhancing model performance while preserving data privacy. We further optimize client-side loss functions to enhance model performance. Theoretical analysis establishes the convergence bounds for FedLRDP, demonstrating its superior convergence performance. Experimental results on MNIST reveal that FedLRDP improves model accuracy by 3.28% compared to traditional DP methods while mitigating MIA with a 72.48% lower attack success rate than FedAvg. Moreover, on EMNIST, FedLRDP boosts model accuracy by 7.31% compared to traditional DP methods, maintaining a 59.4% lower attack success rate than FedAvg. These findings underscore FedLRDP’s efficacy in meeting client privacy needs while enhancing model performance.

关键词： Training Differential privacy Privacy Accuracy Federated learning Noise Data models