检索结果-内蒙古大学图书馆

Applying regression techniques in designing optimal trade execution strategy for an asset

OPTIMIZATION 2022年第3期71卷 463-484页

作者： Sehgal, Ruchika Mehra, Aparna Indian Inst Technol Delhi Dept Math New Delhi India

The paper aims to construct an optimal trading strategy for procuring a large but fixed volume of a risky asset. The proposed approach splits a large block of trade into smaller packages to minimize the execution cost of the trade. In this study, we suggest an incipient price dynamics for the asset where we express its current market price as a convex combination of the price impervious to our anterior trade in the asset and the execution price carrying the impact of our anterior trade in it. We propose to apply the regression techniques to estimate the unaffected price of the asset. The formulated model is a convex quadratic optimization problem and thus computationally tractable. We evaluate the performance of the proposed model on five stocks namely, Apple, Microsoft, Coca-Cola, Amazon, and Netflix and conclude that the proposed model consistently achieves a lower execution cost than the one obtained from some other models existing in the literature.

关键词： Optimal trade execution problem price dynamics of an asset quadratic programming problem quantile regression support vector quantile regression

来源：评论

学校读者我要写书评

暂无评论

Probability of entering an orthant by correlated fractional Brownian motion with drift: exact asymptotics

引用

EXTREMES 2024年第4期27卷 613-641页

作者： Debicki, Krzysztof Ji, Lanpeng Novikov, Svyatoslav Univ Wroclaw Math Inst Pl Grunwaldzki 2-4 PL-50384 Wroclaw Poland Univ Leeds Sch Math Woodhouse Lane Leeds LS2 9JT England Univ Lausanne Dept Actuarial Sci UNIL Dorigny CH-1015 Lausanne Switzerland

For {B-H(t)=(B-H,B-1(t),& mldr;,B-H,B-d(t))(inverted perpendicular),t >= 0}, where {B-H,B-i(t),t >= 0},1 = 0:AB(H)(t)-mu t> nu u),u ->infinity, where A is a non-singular dxd matrix and mu=(mu(1),& ... 详细信息

For {B-H(t)=(B-H,B-1(t),& mldr;,B-H,B-d(t))(inverted perpendicular),t >= 0}, where {B-H,B-i(t),t >= 0},1 <= i <= d are mutually independent fractional Brownian motions, we obtain the exact a symptotics of P(there exists t >= 0:AB(H)(t)-mu t> nu u),u ->infinity, where A is a non-singular dxd matrix and mu=(mu(1),& mldr;,mu(d))(inverted perpendicular)is an element of R-d, nu=(nu(1),& mldr;,nu(d))(inverted perpendicular)is an element of R-d are such that there exists some 1 <= i <= d such that mu(i )>0,nu(i )>0.

关键词： Multi-dimensional fractional Brownian motion Extremes Exact asymptotics Large deviations quadratic programming problem Dimension reduction

来源：评论

学校读者我要写书评

暂无评论

On-line Solution of System Constraints in Generalized Predictive Control Design Convenient Way to Cope with Constraints 20

On-line Solution of System Constraints in Generalized Predic...

引用

20th International Conference on Process Control (PC)

作者： Belda, Kvetoslav Acad Sci Czech Republic Inst Informat Theory & Automat Dept Adapt Syst Pod Vodarenskou Vezi 4 Prague 8 Czech Republic

ISBN: (纸本)9781467366274

A specific efficient solution of constrained system outputs is presented. The solution is based on on-line weighting of individual system outputs or output components representing in fact a specific on-line tuning/applification of the components of weighting control parameters. Thus, the predictive control design retains flexibility without any increase of time-computational demands. The proposed solution represents only soft solution of the constraints, i.e. a compliance with the constraints is not fully guaranteed, but the result is satisfactory and not so far from results of hard-constraint solution computed e.g. by a quadratic programming. The solution predetermines the area of the use to the systems with fast dynamics requiring very high sampling rates as electric drives and the like. The solution is presented in the paper as a generalized solution for common use. It is demonstrated by simple simulative examples and one illustration from a real control of 3-phase electric drive.

关键词： Predictive control incremental algorithms system constraints component tuning of control parameters quadratic cost function quadratic programming problem

来源：评论

学校读者我要写书评

暂无评论

Image Inpainting as a quadratic programming Task 6

Image Inpainting as a Quadratic Programming Task

引用

6th International Conference on Information Technology and Nanotechnology (IEEE ITNT)

作者： Myasnikov, Vladislav Verichev, Alexander Samara Natl Res Univ Dept Geoinformat & Informat Secur Samara Russia RAS Image Proc Syst Inst Branch FSRC Crystallog & Photon Samara Russia

ISBN: (数字)9781728170411

ISBN: (纸本)9781728170411

Digital image inpainting is an image restoration technique used to replace missing, damaged, or deteriorated parts of images. Classical textual and structural, as well as deep neural network learning-based, methods have been proposed for inpainting digital images originating from various sources. In this paper we propose a method that falls within the realm of classical methods. The inpainting task is formulated as a quadratic programming problem, and two solution methods, unsupervised and supervised, are described. The proposed methods are experimentally evaluated on the different classes of images. We analyze and discuss the results and identify possible future research directions.

关键词： image inpainting spatial-spectral patterns reconstruction problem quadratic programming problem algorithms

来源：评论

学校读者我要写书评

暂无评论

Free-Form Surface Reconstruction from Arbitrary Perspective Images

Free-Form Surface Reconstruction from Arbitrary Perspective ...

引用

4th IEEE International Advance Computing Conference (IACC)

作者： Saini, Deepika Kumar, Sanjeev Indian Inst Technol Dept Math Roorkee 24667 Uttar Pradesh India

ISBN: (纸本)9781479925711

In this paper, a new algorithm for surface reconstruction from their arbitrary perspective images is presented. An optimization formulation for such type of reconstruction problem, based on a Non-Uniform Rational B-Spline (NURBS) surface model is adopted. It converts reconstruction of a 3D surface into reconstruction of control points and weight vectors of a NURBS representation of the surface. Perspective invariance property of NURBS surface is used to formulate the 3D surface reconstruction problem as a nonlinear optimization problem. The fitting is obtained by solving a quadratic programming problem for finding the weight vectors of NURBS surface and then solving a system of linear equation for finding control points. A comparison study is shown in terms of various type of errors between proposed and triangulation based approach where point-to-point correspondence is required.

关键词： 3D reconstruction Free-form surfaces NURBS Perspective projection quadratic programming problem

来源：评论

学校读者我要写书评

暂无评论

Composite Single-Loop Model Predictive Control Design for PMSM Servo System Speed Regulation Based on Disturbance Observer 32

Composite Single-Loop Model Predictive Control Design for PM...

引用

32nd Chinese Control And Decision Conference (CCDC)

作者： Zhou, Mengdi Liu, Xiangyang Li, Shihua Southeast Univ Sch Automat Key Lab Measurement & Control Complex Syst Engn Minist Educ Nanjing 210096 Peoples R China

ISBN: (纸本)9781728158556

In order to optimize the control performance of the permanent magnet synchronous motor (PMSM) in the presence of strong disturbances and model uncertainty, a composite single-loop model predictive control (MPC) based on disturbance observer (DOB) is studied in this paper. Firstly, a DOB is employed to estimate the lumped disturbance including the uncertain parameters and the external disturbance in real time. Afterwards, benefitting from model-based design, estimations are introduced into the prediction model of the PMSM, then a composite single-loop MPC is designed based on this model. Finally, the optimal control input is obtained, by introducing Lagrange vector and solving the quadratic programming problem with constraints. Simulation results show that the proposed composite control method has a faster transient response and a better disturbance rejection ability. In addition, compared with the generally cascade structure, only the predictive horizon and the observer poles are needed to be adjusted, so it provides a more practical optimization algorithm for the engineering application.

关键词： Composite Single-Loop Model Predictive Control Disturbance Observer quadratic programming problem PMSM Servo System

来源：评论

学校读者我要写书评

暂无评论

A decomposition method for Support Vector Clustering

A decomposition method for Support Vector Clustering

引用

International Conference on Intelligent Sensing and Information Processing

作者： Saradhi, VV Karnik, H Mitra, P Indian Inst Technol CSE New Delhi 110016 India

ISBN: (纸本)0780388402

In this paper we study how to apply decomposition method for Support Vector Clustering (SVC) and compare its performance with that of non-decompensation methods which solves quadratic programming problem using traditional techniques. Decomposition is one of the major methods for solving SVMs and is known for its efficiency. SVC is a novel clustering method that uses SVM approach. SVC problem is formulated as a quadratic optimization with constrains to come up with clusters. When applying SVC to large data sets, traditional ways of solving quadratic programming problem require huge memory and computational time. This problem is eased by the application of the Decomposition method. This paper discusses the application of the decompensation method in such cases and gives a detailed discussion on how to apply the method. The method is applied on a few benchmark data sets and results shows a substantial improvement in terms of performance.

关键词： pattern clustering quadratic programming support vector machines decomposition method quadratic programming problem support vector clustering

来源：评论

学校读者我要写书评

暂无评论

A Two-Norm Squared Fuzzy-Based Least Squares Twin Parametric-Margin Support Vector Machine

A Two-Norm Squared Fuzzy-Based Least Squares Twin Parametric...

引用

International Conference on Machine Intelligence and Signal Processing (MISP)

作者： Borah, Parashjyoti Gupta, Deepak NIT Arunachal Pradesh Comp Sci & Engn Yupia India

ISBN: (纸本)9789811309236;9789811309229

A two-norm squared fuzzy-based least squares version of twin parametric-margin support vector machine is proposed to reduce the effect of outliers and noise by assigning fuzzy membership values to each training data samples. Further, by considering two-norm squared the slack variable multiplied to the fuzzy membership values makes the objective function strongly convex. Here, we substitute the inequality constraints of the primal problems with equality constraints to solve the two primal problems instead of solving two quadratic programming problems which eliminates the need of external optimization toolbox and provides with a lower computational cost. A performance comparison of the proposed method with twin support vector machine, least squares twin support vector machine, twin parametric-margin support vector machine and least squares twin parametric-margin support vector machine is presented in this paper.

关键词： Support vector machine Fuzzy quadratic programming problem Least squares Parametric-margin

来源：评论

学校读者我要写书评

暂无评论

Decision-Making with Interval Probabilities

Decision-Making with Interval Probabilities

引用

IEEE International Conference on System, Man, and Cybernetic

作者： Guo, Peijun Tanaka, Hideo Yokohama Natl Univ Fac Business Adm 79-4 Tokiwadai Yokohama Kanagawa 2408501 Japan Hiroshima Int Univ Fac Psychol Sci Higashihiroshima 7392695 Japan

ISBN: (纸本)9781424423835

In recent years, dealing with uncertainty using interval probabilities is receiving considerable attention by researchers. Most of researches related to interval probabilities, such as combination, marginalization, condition, Bayesian inferences, assume interval probabilities are known. How to elicit interval probabilities from subject is a basic problem for the applications of interval probability theory and till now a computational challenge. In this research, the approaches for estimating interval probabilities are proposed with the pair-wise comparison of the possible outcomes to know which one is more likely to occur. The first method is LP-based one. The second method is QP-based one. Interval expectation, interval entropy are investigated. The decision criteria under interval probabilities are given.

关键词： AHP decision analysis interval probabilities linear programming problem quadratic programming problem

来源：评论

学校读者我要写书评

暂无评论

Monotonic regression filters for trending deterioration faults

Monotonic regression filters for trending deterioration faul...

引用

American Control Conference

作者： Gorinevsky, D Honeywell Labs Fremont CA 94539 USA

ISBN: (纸本)0780383354

This paper describes optimal nonlinear filtering algorithms for recovering trends of system performance variables (fault intensities) from noisy sensor data. A key underlying assumption for the algorithms is that the performance can only deteriorate with time, never improve. This assumption describes accumulating damage to the system components. Mathematically, the trend is obtained as a maximum likelihood estimate of an orbit in a hidden Markov model from the noisy output data. The empirical signal model and the overall problem setup are very close to optimal Kalman filtration. The main difference is that instead of a gaussian noise driving the random model of the fault a one sided exponentially distributed noise is assumed. Such a statistical model leads to a nonlinear batch filter. The trend is estimated by solving a quadratic programming problem. Unlike Kalman filters that can be implemented through recursive computations, the developed algorithms run in a batch mode. Though being more complex computationally, the developed trending algorithms demonstrate performance superior to Kalman filters in the fault trending applications.

关键词： Kalman filters nonlinear filters filtering theory Gaussian noise regression analysis maximum likelihood estimation hidden Markov models exponential distribution quadratic programming monotonic regression filters deterioration fault trend optimal nonlinear filtering algorithms system performance variables noisy sensor data hidden Markov model noisy output data empirical signal model optimal Kalman filtration nonlinear batch filter quadratic programming problem exponential distribution noise

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：