检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Sun, Shengyang Zhang, Yian Bukharin, Alexander Mosallanezhad, David Zeng, Jiaqi Singhal, Soumye Shen, Gerald Renduchintala, Adithya Konuk, Tugrul Dong, Yi Wang, Zhilin Chichkov, Dmitry Delalleau, Olivier Kuchaiev, Oleksii NVIDIA United States

The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces Reward-Aware Preference optimization (RPO), a mathematical framework that unifies popular preference optimization techniques in LLM alignment, including DPO, IPO, SimPO, and REINFORCE (LOO), among others. RPO provides a structured approach to disentangle and systematically study the impact of various design choices—such as the optimization objective, the number of responses per prompt, and the use of implicit versus explicit reward models—on LLM preference optimization. We additionally propose a new experimental setup that enables the clean and direct ablation of such design choices. Through an extensive series of ablation studies within the RPO framework, we gain insights into the critical factors shaping model alignment, offering practical guidance on the most effective strategies for improving LLM alignment. © 2025, CC BY.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

The relevance of breast motions and gaits in running exercises

引用

FASHION AND TEXTILES 2022年第1期9卷 1-21页

作者： Zhou, Jie Mao, Qian Zhang, Jun Lau, Newman M. L. Chen, Jianming Xian Polytech Univ Sch Apparel & Art Design 19 Jinhua South Rd Xian Shaanxi Peoples R China Hong Kong Polytech Univ Sch Design Hung Hom Kowloon Hong Kong Peoples R China Chinese Univ Hong Kong Dept Biomed Engn Shatin Hong Kong Peoples R China

The control of breast motions is a critical indicator to evaluate the comfort and function of sports bras. If the breast motions can be predicted based on the gait parameters detected by wearable sensors, it will more economical and convenient to evaluate the bras. Thirteen unmarried Chinese females with a breast cup of 75B were recruited in this study to investigate the regularity of breast motions and the relevance between breast motions and gaits during running exercises. The breast motion indicator is the distance alteration of breast regions. The gaits were described by the rotation angles of the hip, knee, ankle joints, and the foot height off the ground. Firstly, the Mann-Whitney U test and the Kruskal-Wallis H test were utilized to analyze the motion diversity among the eight breast regions. Then, the gray correlation analysis was applied to explore the relevance between breast motions and gaits. Finally, the back-propagation neural network, the genetic algorithm, and the particle swarm optimization algorithm were utilized to construct the prediction models for breast motions based on gait parameters. The results demonstrate that the same breast regions on the bilateral breasts and the different breast regions on the ipsilateral breasts present a significant motion diversity. There is a moderate correlation between breast motions and gait parameters, and the back-propagation neural network optimized by the particle swarm optimization algorithm performs better in breast motion prediction, which has a coefficient of determination of 84.58% and a mean absolute error of 0.2108.

关键词： Breast motions Gaits Running exercises Back-propagation neural network optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Provably Safe Tolerance Estimation for Robot Arms via Sum-of-Squares Programming

引用

IEEE CONTROL SYSTEMS LETTERS 2022年 6卷 3439-3444页

作者： Zhao, Weiye He, Suqin Liu, Changliu Carnegie Mellon Univ Inst Robot Pittsburgh PA 15213 USA Tsinghua Univ Dept Mech Engn Beijing 100190 Peoples R China

Tolerance estimation problems are prevailing in engineering applications. For example, in modern robotics, it remains challenging to efficiently estimate joint tolerance, i.e., the maximal allowable deviation from a reference robot state such that safety constraints are still satisfied. This letter presents an efficient algorithm to estimate the joint tolerance using sum-of-squares programming. It is theoretically proved that the algorithm provides a lower bound of the joint tolerance. Extensive numerical studies demonstrate that the proposed method is computationally efficient and near optimal.

关键词： Manipulators Estimation Programming optimization Collision avoidance Kinematics Program processors optimization optimization algorithms robotics

来源：评论

学校读者我要写书评

暂无评论

A fusion algorithm based on whale and grey wolf optimization algorithm for solving real-world optimization problems

引用

APPLIED SOFT COMPUTING 2023年 146卷

作者： Yang, Qian Liu, Jinchuan Wu, Zezhong He, Shengyu Chengdu Univ Informat Technol Sch Appl Math Chengdu 610225 Peoples R China Chengdu Univ Informat Technol Sch Software Engn Chengdu 610225 Peoples R China Xichang Univ Chengdu 615000 Peoples R China

In order to better understand and analyze population-based meta-heuristic optimization algorithms, this paper proposed a new hybrid algorithm combined Levy flight with modified Whale optimization Algorithm (WOA) and Grey Wolf Optimizer (GWO) , which is called LMWOAGWO to discard the dross and select the essence. Firstly, the population is initialized by using the uniform distribution space combined with the pseudo-reverse learning strategy, which lays the foundation for global search. Then, modifications were made to both WOA and GWO. For WOA algorithm, random adjustment control parameters strategy and different chaotic maps are used to adjust the main parameters of WOA to avoid the algorithm falling into local optimum in the later stage. For GWO algorithm, a new optimal solution is added to the grey wolf population to increase the optimal update position of the algorithm. On this basis, the dynamic weighting strategy is introduced to improve the convergence accuracy and convergence speed of the algorithm. Subsequently, new conditions were added during the WOA exploitation phase to formulate LMWOAGWO and the greedy strategy is used to retain better iteration update locations. Finally, Levy flight is used to improve the global search ability of the algorithm. Extensive numerical experiments were conducted using 23 standard test benchmark functions, 25 CEC2005 functions, 15 popular benchmark functions and 10 CEC2019 functions to test the performance of LMWOAGWO compared with other well-known swarm optimization algorithms. Experimental and statistical results show that the performance of LMWOAGWO algorithm is better than many state-of-the-art algorithms. Then, 22 real-world optimization problems were used to further study the effectiveness of LMWOAGWO. Winners of CEC2020 Real World Single Objective Constraint optimization Competition, such as iLSHADE & epsilon;algorithm, sCMAgES algorithm, COLSHADE algorithm and EnMODE algorithm are selected as four comparison algorith

关键词： Whale optimization algorithm Grey wolf optimizer optimization algorithms Levy flight Chaotic maps

来源：评论

学校读者我要写书评

暂无评论

Introductory overview: optimization using evolutionary algorithms and other metaheuristics

引用

ENVIRONMENTAL MODELLING & SOFTWARE 2019年第Apr.期114卷 195-213页

作者： Maier, H. R. Razavi, S. Kapelan, Z. Matott, L. S. Kasprzyk, J. Tolson, B. A. Univ Adelaide Sch Civil Environm & Min Engn Adelaide SA 5005 Australia Univ Saskatchewan Global Inst Water Secur Saskatoon SK Canada Univ Saskatchewan Sch Environm & Sustainabil Saskatoon SK Canada Univ Saskatchewan Dept Civil & Geol Engn Saskatoon SK Canada Univ Exeter Coll Engn Math & Phys Sci Harrison BldgNorth Pk Rd Exeter EX4 4QF Devon England SUNY Buffalo Ctr Computat Res Buffalo NY 14203 USA Univ Colorado Civil Environm & Architectural Engn Dept UCB 428 Boulder CO 80309 USA Univ Waterloo Dept Civil & Environm Engn Waterloo ON N2L 3G1 Canada Delft Univ Technol Fac Civil Engn & Geosci Dept Water Management Stevinweg 1 NL-2628 CN Delft Netherlands

Environmental models are used extensively to evaluate the effectiveness of a range of design, planning, operational, management and policy options. However, the number of options that can be evaluated manually is generally limited, making it difficult to identify the most suitable options to consider in decision-making processes. By linking environmental models with evolutionary and other metaheuristic optimization algorithms, the decision options that make best use of scarce resources, achieve the best environmental outcomes for a given budget or provide the best trade-offs between competing objectives can be identified. This Introductory Overview presents reasons for embedding formal optimization approaches in environmental decision-making processes, details how environmental problems are formulated as optimization problems and outlines how single- and multi-objective optimization approaches find good solutions to environmental problems. Practical guidance and potential challenges are also provided.

关键词： Environmental factors Environmental models design scheme evolutionary algorithm optimization algorithms Evolutionary

来源：评论

学校读者我要写书评

暂无评论

Controlled optimization with a Prescribed Finite-Time Convergence Using a Time Varying Feedback Gradient Flow

arXiv

引用

arXiv 2025年

作者： Abdel Aal, Osama F. Özbek, Necdet Sinan Viola, Jairo Chen, YangQuan Dept. of Mechanical Engineering University of California Merced 5200 N. Lake Rd MercedCA95343 United States Adana Alparslan Türkeş Science and Technology University Faculty of Engineering Department of Electrical Electronics Engineering Adana Turkey

From the perspective of control theory, the gradient descent optimization methods can be regarded as a dynamic system where various control techniques can be designed to enhance the performance of the optimization method. In this paper, we propose a prescribed finite-time convergent gradient flow that uses time-varying gain nonlinear feedback that can drive the states smoothly towards the minimum. This idea is different from the traditional finite-time convergence algorithms that relies on fractional-power or signed gradient as a nonlinear feedback, that is proved to have finite/fixed time convergence satisfying strongly convex or the Polyak-Lojasiewicz (PL) inequality, where due to its nature, the proposed approach was shown to achieve this property for both strongly convex function, and for those satisfies Polyak-Lojasiewic inequality. Our method is proved to converge in a prescribed finite time via Lyapunov theory. Numerical experiments were presented to illustrate our results. © 2025, CC BY.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Theoretical Analysis of Analogy-Based Evolutionary Transfer optimization

arXiv

引用

arXiv 2025年

作者： Xue, Xiaoming Feng, Liang Feng, Yinglan Liu, Rui Zhang, Kai Tan, Kay Chen Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong College of Computer Science Chongqing University China School of Civil Engineering Qingdao University of Technology China

Evolutionary transfer optimization (ETO) has been gaining popularity in research over the years due to its outstanding knowledge transfer ability to address various challenges in optimization. However, a pressing issue in this field is that the invention of new ETO algorithms has far outpaced the development of fundamental theories needed to clearly understand the key factors contributing to the success of these algorithms for effective generalization. In response to this challenge, this study aims to establish theoretical foundations for analogy-based ETO, specifically to support various algorithms that frequently reference a key concept known as similarity. First, we introduce analogical reasoning and link its subprocesses to three key issues in ETO. Then, we develop theories for analogy-based knowledge transfer, rooted in the principles that underlie the subprocesses. Afterwards, we present two theorems related to the performance gain of analogy-based knowledge transfer, namely unconditionally nonnegative performance gain and conditionally positive performance gain, to theoretically demonstrate the effectiveness of various analogy-based ETO methods. Last but not least, we offer a novel insight into analogy-based ETO that interprets its conditional superiority over traditional evolutionary optimization through the lens of the no free lunch theorem for optimization. 1156v1 [***] 27 Mar Copyright © 2025, The Authors. All rights reserved.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient Distributed SGD With Compressed Sensing

引用

IEEE CONTROL SYSTEMS LETTERS 2022年 6卷 2054-2059页

作者： Tang, Yujie Ramanathan, Vikram Zhang, Junshan Li, Na Harvard Univ Sch Engn & Appl Sci Allston MA 02134 USA Arizona State Univ Sch Elect Comp & Energy Engn Tempe AZ 85287 USA

We consider large scale distributed optimization over a set of edge devices connected to a central server, where the limited communication bandwidth between the server and edge devices imposes a significant bottleneck for the optimization procedure. Inspired by recent advances in federated learning, we propose a distributed stochastic gradient descent (SGD) type algorithm that exploits the sparsity of the gradient, when possible, to reduce communication burden. At the heart of the algorithm is to use compressed sensing techniques for the compression of the local stochastic gradients at the device side;and at the server side, a sparse approximation of the global stochastic gradient is recovered from the noisy aggregated compressed local gradients. We conduct theoretical analysis on the convergence of our algorithm in the presence of noise perturbation incurred by the communication channels, and also conduct numerical experiments to corroborate its effectiveness.

关键词： Servers Compressed sensing Sensors Stochastic processes Sparse matrices optimization Convergence optimization algorithms large-scale systems distributed optimization compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Dynamic parking space allocation at urban scale: Problem formulation and resolution

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2022年第10期34卷 9576-9590页

作者： Errousso, Hanae El Ouadi, Jihane Alaoui, El Arbi Abdellaoui Benhadou, Siham Res Fdn Dev & Innovat Sci & Engn Casablanca 8118 Morocco HASSAN II Univ Natl & High Sch Elect & Mech Casablanca 8118 Morocco EIGSI Casablanca 20410 Morocco Moulay Ismail Univ Ecole Normale Super Meknes 3104 Morocco

Searching for an available parking space is a major cause of traffic congestion and pollution. Besides, getting a free spot constitutes a primary worry for drivers on the road, which results in their daily discomfort and stress. Therefore, well-designed parking management tools are needed to effectively allocate parking spaces to drivers, especially in dense urban areas. In this perspective, we propose two linear integer programming models for assigning parking spaces to all road users (private vehicles and carriers) while maximizing parking occupancy. The first combinatorial problem attributes to each driver only one parking space while the second one assigns two parking spaces if no space is suitable for that motorist. Feasible solutions are computed in an exact way by improved primal simplex method and in an approximated manner by two metaheuristics (Genetic algorithm and Taboo search) for larger scale applications. However, parking problems still persist when parking requests are not properly balanced between a city's zones, a local gridlock problem arises where certain areas are over-used and others under-used. For this reason, we first redistribute parking demands over urban areas before dedicating one or two spaces to each driver. To do this, we consider both solicitation rates in these areas and coverage ratios of received parking demands. Our parking space allocation solution is just one component of a transportation system heavily backed by information and communication technologies. This system consists of effectively managing a city's parking spaces by predicting and understanding their occupancy patterns. The suggested approach is applied to Casablanca city with several parking scenarios in order to evaluate its effectiveness and test its ability to minimize total walking distance, parking costs as well as unmet demand percentages. Experimental results show that our mathematical models can effectively rule out parking problems. The related published met

关键词： Freight transport Smart system Parking space allocation Integer linear programming Combinatorial problem optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Distributed Forgetting-factor Regret-based Online optimization over Undirected Connected Networks

arXiv

引用

arXiv 2025年

作者： Mo, Lipo Li, Jianjun Zuo, Min Wang, Lei Institute of Systems Science Beijing Wuzi University Beijing101126 China School of Mathematics and Statistics Beijing Technology and Business University Beijing100048 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China

The evaluation of final-iteration tracking performance is a formidable obstacle in distributed online optimization algorithms. To address this issue, this paper proposes a novel evaluation metric named distributed forgetting-factor regret (DFFR). It incorporates a weight into the loss function at each iteration, which progressively reduces the weights of historical loss functions while enabling dynamic weights allocation across optimization horizon. Furthermore, we develop two distributed online optimization algorithms based on DFFR over undirected connected networks: the Distributed Online Gradient-free Algorithm for bandit-feedback problems and the Distributed Online Projection-free Algorithm for high-dimensional problems. Through theoretical analysis, we derive the upper bounds of DFFR for both algorithms and further prove that under mild conditions, DFFR either converges to zero or maintains a tight upper bound as iterations approach infinity. Experimental simulation demonstrates the effectiveness of the algorithms and the superior performance of DFFR. Copyright © 2025, The Authors. All rights reserved.

关键词： optimization algorithms

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：