检索结果-内蒙古大学图书馆

Annual Conference on Neural Information Processing Systems

作者： Ashok Cutkosky Kwabena Boahen Department of Computer Science Stanford University Department of Bioengineering Stanford University

ISBN: (纸本)9781510838819

We propose an online convex optimization algorithm (rescaledexp) that achieves optimal regret in the unconstrained setting without prior knowledge of any bounds on the loss functions. We prove a lower bound showing an exponential separation between the regret of existing algorithms that require a known bound on the loss functions and any algorithm that does not require such knowledge. RESCALEDEXP matches this lower bound asymptotically in the number of iterations. rescaledexp is naturally hyperparameter-free and we demonstrate empirically that it matches prior optimization algorithms that require hyperparameter optimization.

关键词： LOSS FUNCTION Regret optimization algorithms algorithms Prior Learning Lower bound asymptotic Require Hyperparameter Bound domains Phyla

来源：评论

学校读者我要写书评

暂无评论

optimization Algorithm for Vehicle Braking Force Distribution of Front and Rear Axles Based on Brake Strength

Optimization Algorithm for Vehicle Braking Force Distributio...

引用

World Congress on Intelligent Control and Automation

作者： Jinlong Xu Xiangwen Zhang School of Electrical Engineering and Automation Guilin University of Electronic Technology Guilin 541000 China School of Electronic Engineering and Automation Guilin University of Electronic Technology Guilin 541000 China

ISBN: (纸本)9781467384155

The vehicle braking force distribution of front and rear axles affects its safety directly. In order to enhance the braking safety, the changes of brake strength are considered in this paper, and an optimization algorithm for braking force distribution is designed. The method is the variable ratio method, and it can change the braking force distribution rate of front and rear axles according to the brake strength variation, so its braking effect can be optimal. To verify the validity of the algorithm, two braking force distribution algorithm models with the fixed ratio and variable ratio were built in Matlab/Simulink respectively, and the simulation test was done based on the ASM model of dSPACE. The result show that the optimization distribution algorithm with variable ratio has better stability of braking direction, and higher adhesion coefficient utilization and shorter braking distance. Therefore, the optimization braking force distribution algorithm with the variable ratio is a promising method, and it can be used to improve the braking performance effectively, thereby to improve the vehicle safety ultimately.

关键词： Force Vehicles Wheels Adhesives Brakes Algorithm design and analysis optimization Brake variable ratio Algorithm design and analysis optimization algorithms Wheels rear axle vehicle Force adhesives Braking braking force vehicle brakes Axle simulation test Allocation Algorithm

来源：评论

学校读者我要写书评

暂无评论

Stochastic optimization for Large-scale Optimal Transport 16

Stochastic Optimization for Large-scale Optimal Transport

引用

Annual Conference on Neural Information Processing Systems

作者： Aude Genevay Marco Cuturi Gabriel Peyre Francis Bach CEREMADE Universite Paris-Dauphine INRIA - Mokaplan project-team CREST ENSAE Universite Paris-Saclay CNRS and DMA Ecole Normale Superieure INRIA - Mokaplan project-team INRIA - Sierra project-team DI ENS

ISBN: (纸本)9781510838819

Optimal transport (OT) defines a powerful framework to compare probability distributions in a geometrically faithful way. However, the practical impact of OT is still limited because of its computational burden. We propose a new class of stochastic optimization algorithms to cope with large-scale OT problems. These methods can handle arbitrary distributions (either discrete or continuous) as long as one is able to draw samples from them, which is the typical setup in high-dimensional learning problems. This alleviates the need to discretize these densities, while giving access to provably convergent methods that output the correct distance without discretization error. These algorithms rely on two main ideas: (a) the dual OT problem can be re-cast as the maximization of an expectation; (b) the entropic regularization of the primal OT problem yields a smooth dual optimization which can be addressed with algorithms that have a provably faster convergence. We instantiate these ideas in three different setups: (i) when comparing a discrete distribution to another, we show that incremental stochastic optimization schemes can beat Sinkhorn's algorithm, the current state-of-the-art finite dimensional OT solver; (ii) when comparing a discrete distribution to a continuous density, a semi-discrete reformulation of the dual program is amenable to averaged stochastic gradient descent, leading to better performance than approximately solving the problem by discretization ; (iii) when dealing with two continuous densities, we propose a stochastic gradient descent over a reproducing kernel Hilbert space (RKHS). This is currently the only known method to solve this problem, apart from computing OT on finite samples. We backup these claims on a set of discrete, semi-discrete and continuous benchmark problems.

关键词： output transformer optimization algorithms Stochastic discrete data discretization error Benchmark testing algorithms discrete element Probability distribution

来源：评论

学校读者我要写书评

暂无评论

A Competitive QUasi-Affine TRansformation Evolutionary (C-QUATRE) Algorithm for Global optimization

A Competitive QUasi-Affine TRansformation Evolutionary (C-QU...

引用

IEEE International Conference on Systems, Man, and Cybernetics

作者： Zhenyu Meng Jeng-Shyang Pan Department of Computer Science and Technology Harbin Institute of Technology Shenzhen Graduate School Shenzhen China 518055 Department of Computer Science and Technology Harbin Institute of Technology Shenzhen Graduate School Shenzhen China 518055 Fujian Provincial Key Laboratory of Data Mining and Applications Fujian University of Technology Fuzhou China 350000

ISBN: (纸本)9781509018987

In this paper, we proposed a Competitive QUasi-Affine TRansformation Evolutionary (C-QUATRE) algorithm. This algorithm is an advancement of a preciously proposed QUATRE algorithm. The QUATRE algorithm is arguably a very powerful stochastic optimization algorithm, and it will appear in CEC2016 conference proceedings with the paper title "QUasi-Affine TRansformation Evolutionary (QUATRE) Algorithm: A Parameter-reduced Differential Evolution Algorithm for optimization Problem". It conquers some weaknesses of Differential Evolution (DE) algorithm and it has excellent performance even on multi-modal optimization problem. Here in the paper, we advance a C-QUATRE algorithm which uses a pairwise competition mechanism to enhance the performance of the former proposed QUATRE algorithm. The C-QUATRE algorithm is verified both on CEC2013 test suite for realparameter optimization and BBOB2009 framework for blackbox optimization, and experiment results show that the pairwise competition mechanism is very useful for the enhancement of the QUATRE performance over all these benchmarks.

关键词： mechanism enhancement advancement Global optimization algorithms Evolutionary Refractive surgery enhancement BENCHMARKS optimization algorithms paper Pairwise

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE SEQUENTIAL optimization WITH APPLICATIONS TO MACHINE LEARNING

ADAPTIVE SEQUENTIAL OPTIMIZATION WITH APPLICATIONS TO MACHIN...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Craig Wilson Venugopal V. Veeravalli Coordinated Science Lab and Electrical and Computer Engineering University of Illinois at Urbana-Champaign

ISBN: (纸本)9781479999897

A framework is introduced for solving a sequence of slowly changing optimization problems, including those arising in regression and classification applications, using optimization algorithms such as stochastic gradient descent (SGD). The optimization problems change slowly in the sense that the minimizers change at either a fixed or bounded rate. A method based on estimates of the change in the minimizers and properties of the optimization algorithm is introduced for adaptively selecting the number of samples needed from the distributions underlying each problem in order to ensure that the excess risk, i.e., the expected gap between the loss achieved by the approximate minimizer produced by the optimization algorithm and the exact minimizer, does not exceed a target level. Experiments with synthetic and real data are used to confirm that this approach performs well.

关键词： stochastic optimization gradient methods machine learning adaptive algorithms optimization algorithms Adaptive algorithms gradient methods Machine Learning Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

optimization-Enabled EMT Modeling for Transformer Impulse Test

Optimization-Enabled EMT Modeling for Transformer Impulse Te...

引用

IEEE Power and Energy Society General Meeting

作者： Kasun Samarawickrama Aniruddha M. Gole Behzad Kordi Nathan D. Jacob Department of Electrical and Computer Engineering University of Manitoba Winnipeg Canada R3T 5V6 High Voltage Test Facility Manitoba Hydro Winnipeg Canada R3T 1Y6

ISBN: (纸本)9781509041695

A novel method is proposed to enhance the performance of optimization algorithms to obtain impulse generator settings. This method resolves two major problems encountered in tradition optimization-enabled electromagnetic transient simulation (OE-EMTS) approach. First, a new technique is introduced to model a transformer in an electromagnetic transient (EMT) simulator. This technique uses the frequency response of the transformer to calculate time-domain quantities without synthesizing the transformer circuit. As a results, most of the major issues attributed to the frequency-response based EMT modeling are solved, such as appearance of negative resistive elements in the synthesized circuit and generation of highly complex/dense branch networks. Second, multiple optimization algorithms are implemented to optimize impulse generator settings. Combination of multiple algorithms has balanced the effects of convergence speed and accuracy for better results. The proposed approach is verified by two case studies, involving different resistor arrangements. The simulated waveforms are compared with those obtained from measurements.

关键词： Resistors Power transformers Generators optimization Convolution Genetic algorithms Integrated circuit modeling Resistor Device Component integrated circuit modelling dynamos ELECTRIC TRANSFORMERS frequency response Convolution Genetic Algorithm (GA) Transformer optimization algorithms Emergency Medical Technicians ITK gene SLC22A3 gene Pulses Electromagnetic transients

来源：评论

学校读者我要写书评

暂无评论

GPU-BASED optimization FOR SAMPLE ADAPTIVE OFFSET IN HEVC

GPU-BASED OPTIMIZATION FOR SAMPLE ADAPTIVE OFFSET IN HEVC

引用

IEEE International Conference on Image Processing

作者： Yang Wang Xun Guo Yan Lu Xiaopeng Fan Debin Zhao Harbin Institute of Technology Microsoft Research

ISBN: (纸本)9781467399623

The latest high efficiency video coding (HEVC) standard achieves about 50% bit-rate reduction at equivalent visual quality compared to H.264/AVC. Sample adaptive offset (SAO) is one of the newly adopted tools right after deblocking filter, which can improve both coding efficiency and visual quality. However, for real-time encoding scenarios, the complexity of SAO is usually too high to be enabled. In this paper, a GPU-based optimization algorithm is proposed to reduce the complexity of SAO. Experiments are conducted based on the state-of-the-art open source HEVC encoder, i.e. X265. Results show that the proposed algorithm can reduce about 70% processing time of SAO on average without sacrifice of coding efficiency.

关键词： HEVC SAO GPU X265 High efficiency video coding offsets GRAPPER PICK UP Graphics Processing Unit real-time coding optimization algorithms code efficiency coding

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Flux Barrier and Skew Design optimization of Reluctance Synchronous Machines

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2015年第5期51卷 3751-3760页

作者： Howard, Eduan Kamper, Maarten J. Gerber, Stiaan Univ Stellenbosch Dept Elect & Elect Engn ZA-7602 Stellenbosch South Africa

In this paper, an investigation into an alternative topology for reluctance synchronous machine rotor flux barriers is presented. The investigated topology employs a high number of flux barrier variables with an alternative asymmetric rotor structure. The focus in this paper is on maximizing average torque and minimizing torque ripple, using finite element-based design optimization, in order to study the possibility of achieving acceptably low torque ripple. A subsequent investigation into the effect of rotor skew on the proposed optimized design to reduce torque ripple even further is also conducted, as well as the manufacturing and testing of the proposed flux barrier prototype.

关键词： AC motors asymmetric flux barrier asymmetric pole structure finite-element analysis optimization algorithms rotor skew synchronous reluctance machine

来源：评论

学校读者我要写书评

暂无评论

An Improved Evolution Based optimization Algorithm Originated from the Concept of SFLA and Simulated Annealing

An Improved Evolution Based Optimization Algorithm Originate...

引用

IEEE International Conference on Industrial and Information Systems

作者： Sugandha Rathi Vikash Singh Rajput Sandeep Gupta Dept. of Computer Science Engineering Institute of Technology & Management India Dept. of Computer Science Engineering SATI India

The paper shows the contribution of evolutionary techniques in the field of optimization. Evolution is a technique which is based on real-world scenarios. It works on Darwin's theory and many algorithms have been proposed in this field to optimize the results. Each algorithm proposed has its advantages and disadvantages and a new technique is brought to overcome the drawbacks of the previously proposed technique. In this paper, a new approach is proposed based on SFLA and simulated annealing which works on memetic and PSO approaches along with basic temperature idea of simulated annealing. The graphs are attached to show the various results obtained. It is shown that it is better than other algorithms in various factors.

关键词： Sociology Statistics Simulated annealing Genetic algorithms Temperature Algorithm design and analysis simulated annealing Algorithm design and analysis Sociology Genetic Algorithm (GA) optimization algorithms Temperature

来源：评论

学校读者我要写书评

暂无评论

A Novel Global optimization Algorithm and Its Application to Airfoil optimization

引用

JOURNAL OF TURBOMACHINERY-TRANSACTIONS OF THE ASME 2015年第4期137卷 041011页

作者： Yang, B. Xu, Q. He, L. Zhao, L. H. Gu, Ch. G. Ren, P. Shanghai Jiao Tong Univ Gas Turbine Inst Shanghai 200000 Peoples R China Shanghai Elect Power Generat R&D Ctr Shanghai 201612 Peoples R China Shanghai Jiao Tong Univ Sch Mech Engn Shanghai 200000 Peoples R China

In this paper, a novel global optimization algorithm has been developed, which is named as particle swarm optimization combined with particle generator (PSO-PG). In PSO-PG, a PG was introduced to iteratively generate the initial particles for PSO. Based on a series of comparable numerical experiments, it was convinced that the calculation accuracy of the new algorithm as well as its optimization efficiency was greatly improved in comparison with those of the standard PSO. It was also observed that the optimization results obtained from PSO-PG were almost independent of some critical coefficients employed in the algorithm. Additionally, the novel optimization algorithm was adopted in the airfoil optimization. A special fitness function was designed and its elements were carefully selected for the low-velocity airfoil. To testify the accuracy of the optimization method, the comparative experiments were also carried out to illustrate the difference of the aerodynamic performance between the optimized and its initial airfoil.

关键词： Weight (Mass) optimization Particulate matter Fan Compressor Turbine aerodynamic design Particle swarm optimization optimization algorithms Inertia (Mechanics) Airfoils 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：