Classical sequential ranking-and-selection (R&S) procedures require all pairwise comparisons after collecting one additional observation from each surviving system, which is typically an O(k2) operation where k is the number of systems. When the number of systems is large (e.g., millions), these comparisons can be very costly and may significantly slow down the R&S procedures. In this paper we revise KN procedure slightly and show that one may reduce the computational complexity of all pairwise comparisons to an O(k) operation, thus significantly reducing the computational burden. Numerical experiments show that the computational time reduces by orders of magnitude even for moderate numbers of systems.
{"title":"Speeding up pairwise comparisons for large scale ranking and selection","authors":"L. Hong, Jun Luo, Ying Zhong","doi":"10.5555/3042094.3042199","DOIUrl":"https://doi.org/10.5555/3042094.3042199","url":null,"abstract":"Classical sequential ranking-and-selection (R&S) procedures require all pairwise comparisons after collecting one additional observation from each surviving system, which is typically an O(k2) operation where k is the number of systems. When the number of systems is large (e.g., millions), these comparisons can be very costly and may significantly slow down the R&S procedures. In this paper we revise KN procedure slightly and show that one may reduce the computational complexity of all pairwise comparisons to an O(k) operation, thus significantly reducing the computational burden. Numerical experiments show that the computational time reduces by orders of magnitude even for moderate numbers of systems.","PeriodicalId":367269,"journal":{"name":"2016 Winter Simulation Conference (WSC)","volume":"50 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120987496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-11DOI: 10.1109/WSC.2016.7822130
M. Fu
In March of 2016, Google DeepMind's AlphaGo, a computer Go-playing program, defeated the reigning human world champion Go player, 4-1, a feat far more impressive than previous victories by computer programs in chess (IBM's Deep Blue) and Jeopardy (IBM's Watson). The main engine behind the program combines machine learning approaches with a technique called Monte Carlo tree search. Current versions of Monte Carlo tree search used in Go-playing algorithms are based on a version developed for games that traces its roots back to the adaptive multi-stage sampling simulation optimization algorithm for estimating value functions in finite-horizon Markov decision processes (MDPs) introduced by Chang et al. (2005), which was the first use of Upper Confidence Bounds (UCBs) for Monte Carlo simulation-based solution of MDPs. We review the main ideas in UCB-based Monte Carlo tree search by connecting it to simulation optimization through the use of two simple examples: decision trees and tic-tac-toe.
{"title":"AlphaGo and Monte Carlo tree search: The simulation optimization perspective","authors":"M. Fu","doi":"10.1109/WSC.2016.7822130","DOIUrl":"https://doi.org/10.1109/WSC.2016.7822130","url":null,"abstract":"In March of 2016, Google DeepMind's AlphaGo, a computer Go-playing program, defeated the reigning human world champion Go player, 4-1, a feat far more impressive than previous victories by computer programs in chess (IBM's Deep Blue) and Jeopardy (IBM's Watson). The main engine behind the program combines machine learning approaches with a technique called Monte Carlo tree search. Current versions of Monte Carlo tree search used in Go-playing algorithms are based on a version developed for games that traces its roots back to the adaptive multi-stage sampling simulation optimization algorithm for estimating value functions in finite-horizon Markov decision processes (MDPs) introduced by Chang et al. (2005), which was the first use of Upper Confidence Bounds (UCBs) for Monte Carlo simulation-based solution of MDPs. We review the main ideas in UCB-based Monte Carlo tree search by connecting it to simulation optimization through the use of two simple examples: decision trees and tic-tac-toe.","PeriodicalId":367269,"journal":{"name":"2016 Winter Simulation Conference (WSC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121217168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-11DOI: 10.1109/WSC.2016.7822118
Marko A. Hofmann
Several papers have recently criticized the use of null hypothesis significance testing (NHST) in scientific applications of stochastic computer simulation. Their criticism can be underpinned by numerous articles from statistical methodologists. They have argued that focusing on p-values is not conducive to science, and that NHST is often dangerously misunderstood. A critical reflection of the arguments contra NHST shows, however, that although NHST is indeed ill-suited for many simulation applications and objectives it is by no means superfluous, neither in general, nor in particular for simulation.
{"title":"Null hypothesis significance testing in simulation","authors":"Marko A. Hofmann","doi":"10.1109/WSC.2016.7822118","DOIUrl":"https://doi.org/10.1109/WSC.2016.7822118","url":null,"abstract":"Several papers have recently criticized the use of null hypothesis significance testing (NHST) in scientific applications of stochastic computer simulation. Their criticism can be underpinned by numerous articles from statistical methodologists. They have argued that focusing on p-values is not conducive to science, and that NHST is often dangerously misunderstood. A critical reflection of the arguments contra NHST shows, however, that although NHST is indeed ill-suited for many simulation applications and objectives it is by no means superfluous, neither in general, nor in particular for simulation.","PeriodicalId":367269,"journal":{"name":"2016 Winter Simulation Conference (WSC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125437852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-11DOI: 10.1109/WSC.2016.7822248
Gabriela Martinez, T. Huschka, M. Sir, K. Pasupathy
This paper presents a scheduling policy that aims to reduce patient wait time for surgical treatment by coordinating clinical and surgical appointments. This study is of interest since the lack of coordination of these resources could lead to an inefficient utilization of available capacity, and most importantly, could cause delays in patient access to surgical treatment. A simulation model is used to analyze the impact of the policy on patient access and surgical throughput.
{"title":"A coordinated scheduling policy to improve patient access to surgical services","authors":"Gabriela Martinez, T. Huschka, M. Sir, K. Pasupathy","doi":"10.1109/WSC.2016.7822248","DOIUrl":"https://doi.org/10.1109/WSC.2016.7822248","url":null,"abstract":"This paper presents a scheduling policy that aims to reduce patient wait time for surgical treatment by coordinating clinical and surgical appointments. This study is of interest since the lack of coordination of these resources could lead to an inefficient utilization of available capacity, and most importantly, could cause delays in patient access to surgical treatment. A simulation model is used to analyze the impact of the policy on patient access and surgical throughput.","PeriodicalId":367269,"journal":{"name":"2016 Winter Simulation Conference (WSC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123994472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-11DOI: 10.1109/WSC.2016.7822256
V. Augusto, Xiaolan Xie, M. Prodel, B. Jouaneton, L. Lamarsalle
The analysis of clinical pathways from event logs provides new insights about care processes. In this paper, we propose a new methodology to automatically perform simulation analysis of patients' clinical pathways based on a national hospital database. Process mining is used to build highly representative causal nets, which are then converted to state charts in order to be executed. A joint multi-agent discrete-event simulation approach is used to implement models. A practical case study on patients having cardiovascular diseases and eligible to receive an implantable defibrillator is provided. A design of experiments has been proposed to study the impact of medical decisions, such as implanting or not a defibrillator, on the relapse rate, the death rate and the cost. This approach has proven to be an innovative way to extract knowledge from an existing hospital database through simulation, allowing the design and test of new scenarios.
{"title":"Evaluation of discovered clinical pathways using process mining and joint agent-based discrete-event simulation","authors":"V. Augusto, Xiaolan Xie, M. Prodel, B. Jouaneton, L. Lamarsalle","doi":"10.1109/WSC.2016.7822256","DOIUrl":"https://doi.org/10.1109/WSC.2016.7822256","url":null,"abstract":"The analysis of clinical pathways from event logs provides new insights about care processes. In this paper, we propose a new methodology to automatically perform simulation analysis of patients' clinical pathways based on a national hospital database. Process mining is used to build highly representative causal nets, which are then converted to state charts in order to be executed. A joint multi-agent discrete-event simulation approach is used to implement models. A practical case study on patients having cardiovascular diseases and eligible to receive an implantable defibrillator is provided. A design of experiments has been proposed to study the impact of medical decisions, such as implanting or not a defibrillator, on the relapse rate, the death rate and the cost. This approach has proven to be an innovative way to extract knowledge from an existing hospital database through simulation, allowing the design and test of new scenarios.","PeriodicalId":367269,"journal":{"name":"2016 Winter Simulation Conference (WSC)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126256949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-11DOI: 10.1109/WSC.2016.7822149
F. Vázquez-Abad, L. Fenn
The present paper follows up on Vázquez-Abad (2013), where we applied the ghost simulation model to a public transportation problem. The ghost simulation model replaces faster point processes (passenger arrivals) with a “fluid” model while retaining a discrete event simulation for the rest of the processes (bus dynamics). This is not an approximation, but an exact conditional expectation when the fast process is Poisson. It can be interpreted as a Filtered Monte Carlo method for fast simulation. In the current paper we develop the required theory to implement a mixed optimization procedure to find the optimal fleet size under a stationary probability constraint. It is a hybrid optimization because for each fleet size, the optimal headway is real-valued, while the fleet size is integer-valued. We exploit the structure of the problem to implement a stopped target tracking method combined with stochastic binary search.
{"title":"Mixed optimization for constrained resource allocation, an application to a local bus service","authors":"F. Vázquez-Abad, L. Fenn","doi":"10.1109/WSC.2016.7822149","DOIUrl":"https://doi.org/10.1109/WSC.2016.7822149","url":null,"abstract":"The present paper follows up on Vázquez-Abad (2013), where we applied the ghost simulation model to a public transportation problem. The ghost simulation model replaces faster point processes (passenger arrivals) with a “fluid” model while retaining a discrete event simulation for the rest of the processes (bus dynamics). This is not an approximation, but an exact conditional expectation when the fast process is Poisson. It can be interpreted as a Filtered Monte Carlo method for fast simulation. In the current paper we develop the required theory to implement a mixed optimization procedure to find the optimal fleet size under a stationary probability constraint. It is a hybrid optimization because for each fleet size, the optimal headway is real-valued, while the fleet size is integer-valued. We exploit the structure of the problem to implement a stopped target tracking method combined with stochastic binary search.","PeriodicalId":367269,"journal":{"name":"2016 Winter Simulation Conference (WSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129127269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-11DOI: 10.1109/WSC.2016.7822142
H. Lam, Huajie Qian
We study the empirical likelihood method in constructing statistically accurate confidence bounds for stochastic simulation under nonparametric input uncertainty. The approach is based on positing a pair of distributionally robust optimization, with a suitably averaged divergence constraint over the uncertain input distributions, and calibrated with a χ2-quantile to provide asymptotic coverage guarantees. We present the theory giving rise to the constraint and the calibration. We also analyze the performance of our stochastic optimization algorithm. We numerically compare our approach with existing standard methods such as the bootstrap.
{"title":"The empirical likelihood approach to simulation input uncertainty","authors":"H. Lam, Huajie Qian","doi":"10.1109/WSC.2016.7822142","DOIUrl":"https://doi.org/10.1109/WSC.2016.7822142","url":null,"abstract":"We study the empirical likelihood method in constructing statistically accurate confidence bounds for stochastic simulation under nonparametric input uncertainty. The approach is based on positing a pair of distributionally robust optimization, with a suitably averaged divergence constraint over the uncertain input distributions, and calibrated with a χ2-quantile to provide asymptotic coverage guarantees. We present the theory giving rise to the constraint and the calibration. We also analyze the performance of our stochastic optimization algorithm. We numerically compare our approach with existing standard methods such as the bootstrap.","PeriodicalId":367269,"journal":{"name":"2016 Winter Simulation Conference (WSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130629225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-11DOI: 10.1109/WSC.2016.7822343
Sung-Gil Ko, Woo-Seop Yun, Tae-Eog Lee
The objective of tactical level chemical defense operations is to protect forces from chemical attack and restore combat power. To accomplish the objective of chemical defense, combat units, higher level command, chemical protective weapons and support units must perform their respective roles and also cooperate with each other. The aim of this study is to the evaluate the effect of factors affecting chemical operations. This study presents a chemical defense operations model using a DEVS formalism and its virtual experiments. The virtual experiments evaluated protection effectiveness by varying chemical operation factors such as 1) detection range, 2) MOPP transition time, 3) NBC report make-up time, 4) report transmission time, and 5) chemical reconnaissance patrol time. The results of the experiments showed that chemical reconnaissance patrol time and communication time are as important as detection range in terms of strength preservation.
{"title":"Modeling and simulation-based analysis of effectiveness of tactical level chemical defense operations","authors":"Sung-Gil Ko, Woo-Seop Yun, Tae-Eog Lee","doi":"10.1109/WSC.2016.7822343","DOIUrl":"https://doi.org/10.1109/WSC.2016.7822343","url":null,"abstract":"The objective of tactical level chemical defense operations is to protect forces from chemical attack and restore combat power. To accomplish the objective of chemical defense, combat units, higher level command, chemical protective weapons and support units must perform their respective roles and also cooperate with each other. The aim of this study is to the evaluate the effect of factors affecting chemical operations. This study presents a chemical defense operations model using a DEVS formalism and its virtual experiments. The virtual experiments evaluated protection effectiveness by varying chemical operation factors such as 1) detection range, 2) MOPP transition time, 3) NBC report make-up time, 4) report transmission time, and 5) chemical reconnaissance patrol time. The results of the experiments showed that chemical reconnaissance patrol time and communication time are as important as detection range in terms of strength preservation.","PeriodicalId":367269,"journal":{"name":"2016 Winter Simulation Conference (WSC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130652923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we consider the simulation budget allocation problem to maximize the probability of selecting the best simulated design in ordinal optimization. This problem has been studied extensively on the basis of the normal distribution. In this research, we consider the budget allocation problem when the underlying distribution is exponential. This case is widely seen in simulation practice. We derive an asymptotic closed-form allocation rule which is easy to compute and implement in practice, and provide some useful insights for the optimal budget allocation problem with exponential underlying distribution.
{"title":"Optimal computing budget allocation with exponential underlying distribution","authors":"Fei Gao, Siyang Gao","doi":"10.5555/3042094.3042191","DOIUrl":"https://doi.org/10.5555/3042094.3042191","url":null,"abstract":"In this paper, we consider the simulation budget allocation problem to maximize the probability of selecting the best simulated design in ordinal optimization. This problem has been studied extensively on the basis of the normal distribution. In this research, we consider the budget allocation problem when the underlying distribution is exponential. This case is widely seen in simulation practice. We derive an asymptotic closed-form allocation rule which is easy to compute and implement in practice, and provide some useful insights for the optimal budget allocation problem with exponential underlying distribution.","PeriodicalId":367269,"journal":{"name":"2016 Winter Simulation Conference (WSC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116699438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-12-11DOI: 10.1109/WSC.2016.7822102
H. Yao, L. Rojas-Nandayapa, T. Taimre
We consider the problem of estimating tail probabilities of random sums of infinite mixtures of phase-type (IMPH) distributions—a class of distributions corresponding to random variables which can be represented as a product of an arbitrary random variable with a classical phase-type distribution. Our motivation arises from applications in risk and queueing problems. Classical rare-event simulation algorithms cannot be implemented in this setting because these typically rely on the availability of the CDF or the MGF, but these are difficult to compute or not even available for the class of IMPH distributions. In this paper, we address these issues and propose alternative simulation methods for estimating tail probabilities of random sums of IMPH distributions; our algorithms combine importance sampling and conditional Monte Carlo methods. The empirical performance of each method suggested is explored via numerical experimentation.
{"title":"Estimating tail probabilities of random sums of infinite mixtures of phase-type distributions","authors":"H. Yao, L. Rojas-Nandayapa, T. Taimre","doi":"10.1109/WSC.2016.7822102","DOIUrl":"https://doi.org/10.1109/WSC.2016.7822102","url":null,"abstract":"We consider the problem of estimating tail probabilities of random sums of infinite mixtures of phase-type (IMPH) distributions—a class of distributions corresponding to random variables which can be represented as a product of an arbitrary random variable with a classical phase-type distribution. Our motivation arises from applications in risk and queueing problems. Classical rare-event simulation algorithms cannot be implemented in this setting because these typically rely on the availability of the CDF or the MGF, but these are difficult to compute or not even available for the class of IMPH distributions. In this paper, we address these issues and propose alternative simulation methods for estimating tail probabilities of random sums of IMPH distributions; our algorithms combine importance sampling and conditional Monte Carlo methods. The empirical performance of each method suggested is explored via numerical experimentation.","PeriodicalId":367269,"journal":{"name":"2016 Winter Simulation Conference (WSC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131041915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：