检索结果-内蒙古大学图书馆

Efficient Last-iterate Convergence Algorithms in Solving Games

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Meng, Linjian Ge, Zhenxing Li, Wenbin An, Bo Gao, Yang National Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Engineering Nanyang Technological University Singapore

No-regret algorithms are popular for learning Nash equilibrium (NE) in two-player zero-sum normal-form games (NFGs) and extensive-form games (EFGs). However, most of them only have average-iterate convergence, which implies they must average strategies. Averaging strategies increases computational and memory overhead. Importantly, it may also cause additional representation errors when function approximation is used. Therefore, many recent works consider the last-iterate convergence no-regret algorithms since they do not require such averaging. Among them, the two most famous algorithms are Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weight Update (OMWU). However, OGDA has high per-iteration complexity. OMWU exhibits a lower per-iteration complexity but poorer empirical performance, and its convergence holds only when NE is unique. Recent works propose a Reward Transformation (RT) framework for MWU, which removes the uniqueness condition and achieves competitive performance with OMWU. Unfortunately, the algorithms built by this framework perform worse than OGDA under the same number of iterations, and their convergence guarantee is based on the continuous-time feedback assumption, which does not hold in most scenarios. To address these issues, we provide a closer analysis of the RT framework, which holds for both continuous and discrete-time feedback. We demonstrate that the essence of the RT framework is to transform the problem of learning NE in the original game into a series of strongly convex-concave optimization problems (SCCPs), and the sequence of the saddle points of these SCCPs converges to NE of the original game. We show that the bottleneck of the algorithms built by the RT framework is the speed of solving SCCPs. To improve the RT framework’s empirical performance, we design a novel transformation method to enable the SCCPs can be solved by Regret Matching+ (RM+), a no-regret algorithm with better empirical performance than M

关键词： Continuous time systems

Entirety of Quantum Uncertainty and Its Experimental Verification

学校读者我要写书评

暂无评论

Chinese Physics Letters 2021年第7期38卷 11-16页

作者： Jie Xie Li Zhou Aonan Zhang Huichao Xu Man-Hong Yung Ping Xu Nengkun Yu Lijian Zhang National Laboratory of Solid State Microstructures College of Engineering and Applied Sciences and School of PhysicsNanjing UniversityNanjing 210093China Collaborative Innovation Center of Advanced Microstructures Nanjing UniversityNanjing 210093China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Shenzhen Institute for Quantum Science and Engineering and Department of Physics Southern University of Science and TechnologyShenzhen 518055China Shenzhen Key Laboratory of Quantum Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Institute for Quantum Information&State Key Laboratory of High Performance Computing College of ComputerNational University of Defense TechnologyChangsha 410073China Centre for Quantum Software and Information School of SoftwareFaculty of Engineering and Information TechnologyUniversity of Technology SydneyNSWAustralia

As a foundation of quantum physics,uncertainty relations describe ultimate limit for the measurement uncertainty of incompatible ***,uncertainty relations are formulated by mathematical bounds for a specific *** we present a method for geometrically characterizing uncertainty relations as an entire area of variances of the observables,ranging over all possible input *** find that for the pair of position and momentum operators,Heisenberg's uncertainty principle points exactly to the attainable area of the variances of position and ***,for finite-dimensional systems,we prove that the corresponding area is necessarily semialgebraic;in other words,this set can be represented via finite polynomial equations and inequalities,or any finite union of such *** particular,we give the analytical characterization of the areas of variances of(a)a pair of one-qubit observables and(b)a pair of projective observables for arbitrary dimension,and give the first experimental observation of such areas in a photonic system.

关键词： observable union operators

Optimal and Efficient Algorithms for Decentralized Online Convex Optimization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wan, Yuanyu Wei, Tong Xue, Bo Song, Mingli Zhang, Lijun School of Software Technology Zhejiang University Ningbo China State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Computer Science and Engineering Southeast University Nanjing China Department of Computer Science City University of Hong Kong Hong Kong National Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Artificial Intelligence Nanjing University Nanjing China

We investigate decentralized online convex optimization (D-OCO), in which a set of local learners are required to minimize a sequence of global loss functions using only local computations and communications. Previous studies have established O(n5/4ρ−1/2√T) and O(n3/2ρ−1 log T) regret bounds for convex and strongly convex functions respectively, where n is the number of local learners, ρ √T) for convex functions and Ω(n) for strongly convex functions. To fill these gaps, in this paper, we first develop a novel D-OCO algorithm that can respectively reduce the regret bounds for convex and strongly convex functions to Õ(nρ−1/4√T) and Õ(nρ−1/2 log T). The primary technique is to design an online accelerated gossip strategy that enjoys a faster average consensus among local learners. Furthermore, by carefully exploiting spectral properties of a specific network topology, we enhance the lower bounds for convex and strongly convex functions to Ω(nρ−1/4√T) and Ω(nρ−1/2 log T), respectively. These results suggest that the regret of our algorithm is nearly optimal in terms of T, n, and ρ for both convex and strongly convex functions. Finally, we propose a projection-free variant of our algorithm to efficiently handle practical applications with complex constraints. Our analysis reveals that the projection-free variant can achieve O(nT 3/4) and O(nT 2/3(log_ T)1/3) regret bounds for convex and strongly convex functions with nearly optimal Õ(ρ−1/2√T) and Õ(ρ−1/2T 1/3(log T)2/3) communication rounds, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Optimization algorithms

Direct H-He chemical association in superionic FeO2H2He at deep-Earth conditions

学校读者我要写书评

暂无评论

National science Review 2022年第7期9卷 63-70页

作者： Jurong Zhang Hanyu Liu Yanming Ma Changfeng Chen International Center for Computational Method and Software & State Key Laboratory of Superhard Materials & Key Laboratory of Physics and Technology for Advanced Batteries (Ministry of Education) College of Physics Jilin University Shandong Provincial Engineering and Technical Center of Light Manipulations & Shandong Provincial Key Laboratory of Optics and Photonic Device School of Physics and Electronics Shandong Normal University International Center of Future Science Jilin University Department of Physics and Astronomy University of Nevada

Hydrogen and helium are known to play crucial roles in geological and astrophysical environments;however,they are inert toward each other across wide pressure-temperature（P-T） *** their prominent presence and influence on the formation and evolution of celestial bodies,it is of fundamental interest to explore the nature of interactions between hydrogen and *** an advanced crystal structure search method,we have identified a quaternary compound FeO2H2He stabilized in a wide range of P-T *** initio molecular dynamics simulations further reveal a novel superionic state of FeO2H2He hosting liquid-like diffusive hydrogen in the FeO2He sublattice,creating a conducive environment for H-He chemical association,at P-T conditions corresponding to the Earth's lowest mantle *** our surprise,this chemically facilitated coalescence of otherwise immiscible molecular species highlights a promising avenue for exploring this long-sought but hitherto unattainable state of *** finding raises strong prospects for exotic H-He mixtures inside Earth and possibly also in other astronomical bodies.

关键词： high pressure crystal structures molecular dynamics hydrogen-helium chemistry

Norm Augmented Graph AutoEncoders for Link Prediction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Yunhui Zhang, Huaisong Gao, Xinyi Guo, Liuye Tao, Zhen He, Tieke State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China School of Electrical Engineering and Computer Science The University of Queensland Brisbane Australia

Link Prediction (LP) is a crucial problem in graph-structured data. Graph Neural Networks (GNNs) have gained prominence in LP, with Graph AutoEncoders (GAEs) being a notable representation. However, our empirical findings reveal that GAEs’ LP performance suffers heavily from the long-tailed node degree distribution, i.e., low-degree nodes tend to exhibit inferior LP performance compared to high-degree nodes. What causes this degree-related bias, and how can it be mitigated? In this study, we demonstrate that the norm of node embeddings learned by GAEs exhibits variation among nodes with different degrees, underscoring its central significance in influencing the final performance of LP. Specifically, embeddings with larger norms tend to guide the decoder towards predicting higher scores for positive links and lower scores for negative links, thereby contributing to superior performance. This observation motivates us to improve GAEs’ LP performance on low-degree nodes by increasing their embedding norms, which can be implemented simply yet effectively by introducing additional self-loops into the training objective for low-degree nodes. This norm augmentation strategy can be seamlessly integrated into existing GAE methods with light computational cost. Extensive experiments on various datasets and GAE methods show the superior performance of norm-augmented GAEs. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

UT-GAN: A novel Unpaired Textual-Attention Generative Adversarial Network for Low-Light Text Image Enhancement

学校读者我要写书评

暂无评论

UT-GAN: A Novel Unpaired Textual-Attention Generative Advers...

IEEE International Conference on Image Processing

作者： Minglong Xue Zhengyang He Yanyi He Peiqi Xie Xin Feng School of Computer Science and Engineering Chongqing University of Technology Chongqing P.R. China State Key Laboratory for Novel Software Technology Nanjing University Nanjing P.R. China

How to balance lighting and texture details to achieve the desired visual effect remains the bottleneck of existing low-light image enhancement methods. In this paper, we propose a novel Unpaired Textual-attention Generative Adversarial N network (UT-GAN) for low-light text image enhancement task. UT-GAN first uses the Zero-DCE net for initial illumination recovery and our TAM module is proposed to translate text information into a textual attention mechanism for the overall network, emphasizing attention to the details of text regions. Moreover, the method constructs an AGM-Net module to mitigate noise effects and fine-tune the illumination. Experiments show that UT-GAN outperforms existing methods in qualitative and quantitative evaluation on the widely used the low-light datasets LOL and SID.

关键词：

An exploratory study on automatic identification of assumptions in the development of deep learning frameworks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Chen Liang, Peng Ma, Zinan School of Artificial Intelligence Shenzhen Polytechnic University Shenzhen518055 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science Wuhan University Wuhan430072 China Department of Computer Science and Engineering Chalmers University of Technology GothenburgS-412 96 Sweden

Context: Stakeholders constantly make assumptions in the development of deep learning (DL) frameworks. These assumptions are related to various types of software artifacts (e.g., requirements, design decisions, and technical debt) and can turn out to be invalid, leading to system failures. Existing approaches and tools for assumption management usually depend on manual identification of assumptions. However, assumptions are scattered in various sources (e.g., code comments, commits, pull requests, and issues) of DL framework development, and manually identifying assumptions has high costs (e.g., time and resources). Objective: The objective of the study is to evaluate different classification models for the purpose of identification with respect to assumptions from the point of view of developers and users in the context of DL framework projects (i.e., issues, pull requests, and commits) on GitHub. Method: First, we constructed a new and largest dataset (i.e., the AssuEval dataset) of assumptions collected from the TensorFlow and Keras repositories on GitHub. Then we explored the performance of seven non-transformers based models (e.g., Support Vector Machine, Classification and Regression Trees), the ALBERT model, and three decoder-only models (i.e., ChatGPT, Claude, and Gemini) for identifying assumptions on the AssuEval dataset. Results: The study results show that ALBERT achieves the best performance (f1-score: 0.9584) for identifying assumptions on the AssuEval dataset, which is much better than the other models (the 2nd best f1-score is 0.8858, achieved by the Claude 3.5 Sonnet model). Though ChatGPT, Claude, and Gemini are popular models, we do not recommend using them to identify assumptions in DL framework development because of their low performance. Fine-tuning ChatGPT, Claude, Gemini, or other language models (e.g., Llama3, Falcon, and BLOOM) specifically for assumptions might improve their performance for assumption identification. Conclusions: This stu

关键词： Chatbots

Vision Transformer (ViT)-based Applications in Image Classification

学校读者我要写书评

暂无评论

Vision Transformer (ViT)-based Applications in Image Classif...

IEEE International Conference on Big Data Security on Cloud (BigDataSecurity), High Performance and Smart Computing (HPSC) and Intelligent Data and Security (IDS)

作者： Yingzi Huo Kai Jin Jiahong Cai Huixuan Xiong Jiacheng Pang School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China the College of Computer Science and Electronics Engineering Hunan University Changsha China

In recent years, the ViT model has been widely used in the field of computer vision, especially for image classification tasks. This paper summarizes the application of ViT in image classification tasks, first introduces the image classification imple- mentation process and the basic architecture of the ViT model, then analyzes and summarizes the image classification methods, including traditional image classification methods, CNN-based image classification methods, and ViT-based image classification methods, and provides a comparative analysis of CNN and ViT. Subsequently, this paper outlines the application prospects of ViT in image classification and its future development and also outlines some shortcomings of ViT and its solutions.

关键词： Representation learning Analytical models Visualization Computational modeling Transformers Reservoirs Data models

CFC: a Cascade Forest approach to discover Cancer driver genes using multi-omics data

学校读者我要写书评

暂无评论

CFC: a Cascade Forest approach to discover Cancer driver gen...

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Zhang, Lei Yang, Yijing Wang, Zhe Li, Dongdong Liu, Jingping Yang, Hai East China University of Science and Technology Department of Computer Science and Engineering Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China University of Illinois Urbana-Champaign Department of Computer Science ChampaignIL United States

ISBN: (纸本)9781665468190

With the development of next-generation sequencing technology, massive genomic data has been generated, primarily encouraging research on cancer driver genes. Many bioinformatics methods were proposed to identify driver genes. However, the results of driver gene identification a mong these methods show considerable differences. It is still challenging to obtain a comprehensive catalog of cancer drivers. Although current methods have greatly promoted the development of driver genes, few methods can integrate the identification results of existing methods. To solve such problems in cancer driver genes research, we proposed a cascade forest model to discover cancer driver genes(CFC) that can integrate multi-omics data and annotation scores from different cancer driver gene identification algorithms. The proposed method got precise results for 33 cancer types and Pan-cancer. The CFC framework identified 275 driver genes in Pan-cancer, of which 179 were included in the Gold standard. The identified genes were enriched i n t he principal cancer signaling pathways. © 2022 IEEE.

关键词： Genes