Filters








873 Hits in 5.5 sec

Response surface methodology with stochastic constraints for expensive simulation

E Angün, J Kleijnen, D den Hertog, G Gürkan
2009 Journal of the Operational Research Society  
The heuristic is intended for problems in which each simulation run is expensive and the computer budget is limited, so that the search needs to reach a neighborhood of the true optimum quickly.  ...  This paper investigates simulation-based optimization problems with a stochastic objective function, stochastic output constraints, and deterministic input constraints.  ...  for the inventory problem 0.10 quantile 0.25 quantile 0.50 quantile 0.75 quantile 0.90 quantile E[F 0 s * , S * ] − 647.15 /647.15 Proposed search direction RP (or R P ) versus steepest descent RC loop  ... 
doi:10.1057/palgrave.jors.2602614 fatcat:iu3h2mmazreafm7jwqrixwnzua

A GPU Implementation of Parallel Constraint-Based Local Search

Alejandro Arbelaez, Philippe Codognet
2014 2014 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing  
In this paper we study the performance of constraint-based local search solvers on a GPU.  ...  First, by executing multiple copies of the algorithm in a multi-walk manner and, second, by evaluating large neighborhoods in parallel in a single-walk manner.  ...  The first author was supported by the Japan Society for the Promotion of Science (JSPS) under the JSPS Postdoctoral Program and the kakenhi Grant-in-aid for Scientific Research.  ... 
doi:10.1109/pdp.2014.28 dblp:conf/pdp/ArbelaezC14 fatcat:qsn4ujkod5blrox64twnadj3ca

Optimization via Simulation Over Discrete Decision Variables [chapter]

Barry L. Nelson
2010 Risk and Optimization in an Uncertain World  
Continuous-decision-variable OvS, and gradient estimation to support it, has been an active research area with significant advances.  ...  In this tutorial we describe some of the research directions and results available for discretedecision-variable OvS, and provide some guidance for using the OvS heuristics that are built into simulation  ...  Stochastic Constraints For many problems it is natural to have a stochastic constraint E [C(x)] ≤ q.  ... 
doi:10.1287/educ.1100.0069 fatcat:uivi5seqira7xfn6ipx4wui6ma

Continuous optimization via simulation using Golden Region search

Alireza Kabirian, Sigurdur Ólafsson
2011 European Journal of Operational Research  
Linear programming methods: continuous variables with linear known and closed-form functions 2. Linear integer programming methods: discrete variables with linear, known and closed-form functions 3.  ...  Linear mixed integer programming methods: mixed integer variables and linear functions 4. Nonlinear programming: continuous variables and nonlinear functions 5.  ... 
doi:10.1016/j.ejor.2010.09.002 fatcat:rwcven6pwjbnbiki3cjsynmaqu

Stochastic operation of home energy management systems including battery cycling

Carlos Adrian Correa-Florez, Alexis Gerossier, Andrea Michiorri, Georges Kariniotakis
2018 Applied Energy  
The complete two-stage stochastic formulation results in a Mixed-Integer Nonlinear Programming problem that is decomposed using a Competitive Swarm Optimizer to handle the calculation of the battery cycling  ...  A Storage Disaggregation Algorithm based on Lagrangian relaxation is used to reduce the problem size and to allocate individual State of Charge for the batteries.  ...  Acknowledgements This work was carried out as part of the innovation project SENSIBLE (Storage ENabled SustaInable energy for BuiLdings and communitiEs -www.h2020-projectsensible.eu), which has received  ... 
doi:10.1016/j.apenergy.2018.04.130 fatcat:yyr5mwse7rf2bkhx3zp4zlwzm4

Another look at Huber's estimator: A new minimax estimator in regression with stochastically bounded noise

Xuelei Sherry Ni, Xiaoming Huo
2009 Journal of Statistical Planning and Inference  
We develop an alternative asymptotic minimax estimator and name it regression with stochastically bounded noise (RSBN).  ...  Contribution: the generalization of the variational approach is interesting and should be useful in deriving other asymptotic minimax estimators in other problems.  ...  Formulation (2.2) is an l 1 regression with a`dead zone'. By adding some slack variables, (2.2) can be formulated as a linear programming problem.  ... 
doi:10.1016/j.jspi.2008.03.040 fatcat:wj6ndh7r3na5de7m7top3riqw4

Quantile Regression Estimation Using Non-Crossing Constraints

Ilaria Lucrezia Amerise
2018 Journal of Mathematics and Statistics  
In this article we are concerned with a collection of multiple linear regressions that enable the researcher to gain an impression of the entire conditional distribution of a response variable given a  ...  set of explanatory variables.  ...  Acknowledgement The author would like to thank the reviewers for their constructive comments and suggestions. Ethics The Author declares there is not conflict of interest.  ... 
doi:10.3844/jmssp.2018.107.118 fatcat:6acn3u2uhva4bn4oiccohawks4

Spatial Sampling Design and Soil Science [chapter]

Gunter Spock
2011 Principles, Application and Assessment in Soil Science  
The best known methodology for this task of interpolation or map drawing is kriging, also known as best linear unbiased prediction.  ...  Most often a linear trend function m(x)=f(x) T β,w h e r ef(x) is a fixed vector-valued function and β is a regression parameter vector to be estimated, is sufficient for modelling purposes.  ...  In this context a criterion for spatial sampling design with Box-Cox transformed spatial variables is proposed.  ... 
doi:10.5772/30284 fatcat:6xeduvi64vbj7bbkibb747ag3i

Simulation and optimization in production planning

Jack P.C. Kleijnen
1993 Decision Support Systems  
These 28 variables, however, can be reduced to one criterion variable, namely productive machine hours, which is to be maximized, and one commercial variable measuring lead times, which must satisfy a  ...  For this optimization problem the Steepest Ascent technique is applied to the experimental design outcomes. The resulting Response Surface Methodology is developed theoretically.  ...  Acknowledgment I benefitted from the discussions with several company employees and with B. Bettonvil (KUB/TUE) and S. Geldof (ITP-TUE/TNO).  ... 
doi:10.1016/0167-9236(93)90058-b fatcat:fgsvc2vibfhy5e2kkrlwb4kxu4

A computer package for modeling and simulating regionalized count variables

Xavier Emery, Jaime Hernández
2010 Computers & Geosciences  
.  Code available from server at 1 Computer programs are provided for parameter inference and simulation, and an application to a forestry dataset is presented.  ...  Regionalized variables with discrete distributions are commonly associated with counts of individuals (precious stones in ore deposits, wild animals in ecosystems, trees in forests...) that can be represented  ...  Apart from traditional linear kriging, which can be used for both continuous and discrete variables, specific approaches have been developed for dealing with count data, among which one can mention transitive  ... 
doi:10.1016/j.cageo.2009.04.013 fatcat:ytdk7u65nzf43hed4pgmzejx74

Learning to Schedule Heuristics for the Simultaneous Stochastic Optimization of Mining Complexes [article]

Yassine Yaakoubi, Roussos Dimitrakopoulos
2022 arXiv   pre-print
The simultaneous stochastic optimization of mining complexes (SSOMC) is a large-scale stochastic combinatorial optimization problem that simultaneously manages the extraction of materials from multiple  ...  The L2P selects the heuristic (perturbation) to be applied in a self-adaptive manner using reinforcement learning to efficiently explore which local search is best suited for a particular search point.  ...  [19] present a novel imitation learning framework and hypothesize that the state parameterization of the Branch-and-Bound search tree can help solve mixed-integer linear programming (MILP) problems.  ... 
arXiv:2202.12866v1 fatcat:a7oa3bgy7zg6djbr4yeqqmb25a

Asymptotic efficiency of kernel support vector machines (SVM)

V. I. Norkin, M. A. Keyzer
2009 Cybernetics and Systems Analysis  
Note that a solution to stochastic programming and classification problems is usually not unique; therefore, the solution uniqueness assumption means that a fixed (not disappearing with increasing number  ...  An analysis of convergence with respect to a functional is justified for classification problems; however, it is insufficient to consider regression problems such as median and quantile regression [15,  ...  Moreover, for quantile loss functions(2)and(6), problem (13) is convex and nonsmooth; regression errors on observations), it can be reduced to a quadratic programming problem with linear constraints  ... 
doi:10.1007/s10559-009-9125-1 fatcat:xlthnsznjfbrbhmnhqssmfnnsq

Stochastic Spanning

Stelios Arvanitis, Mark Hallam, Thierry Post, Nikolas Topaloglou
2017 Journal of business & economic statistics  
We develop a test procedure for "stochastic spanning" for two nested portfolio sets based on subsampling and linear programming.  ...  Supplementary materials for this article are available online.  ...  ACKNOWLEDGMENTS The authors are grateful to two referees, the associate editor, and the editor for their very helpful comments that have led to this improved version of this study. [ Received October 2015  ... 
doi:10.1080/07350015.2017.1391099 fatcat:jdip5neakfhengwayaqrxwqlmq

Geographically Weighted Quantile Regression (GWQR): An Application to U.S. Mortality Data

Vivian Yi-Ju Chen, Wen-Shuenn Deng, Tse-Chuan Yang, Stephen A. Matthews
2012 Geographical Analysis  
We apply GWQR to U.S. county data as an example, with mortality as the dependent variable and five social determinants as explanatory covariates.  ...  The estimations of GWQR parameters and their standard errors, the cross-validation bandwidth selection criterion, and the non-stationarity test are discussed.  ...  The weighted QR problem defined by equation (8) can be equivalently formulated as a linear programming optimization problem.  ... 
doi:10.1111/j.1538-4632.2012.00841.x pmid:25342860 pmcid:PMC4204738 fatcat:o3cpqxquuvhufphrum76zqncyy

Large Neighborhood Search for Energy Aware Meeting Scheduling in Smart Buildings [chapter]

Boon Ping Lim, Menkes van den Briel, Sylvie Thiébaux, Russell Bent, Scott Backhaus
2015 Lecture Notes in Computer Science  
We extend this work and develop an approach that scales to larger problems by combining mixed integer programming (MIP) with large neighborhood search (LNS).  ...  This approach is far more effective than solving the complete problem as a MIP problem.  ...  Acknowledgments Thanks to Pascal Van Hentenryck for pointing us to optimization problems in the smart buildings space and to Philip Kilby for helpful discussions on LNS.  ... 
doi:10.1007/978-3-319-18008-3_17 fatcat:isyrarmosjcmli25ngnu6aarwa
« Previous Showing results 1 — 15 out of 873 results