{"@context":"http://iiif.io/api/presentation/2/context.json","@id":"https://repo.library.stonybrook.edu/cantaloupe/iiif/2/manifest.json","@type":"sc:Manifest","label":"Adaptive Search Algorithms for Simulation Optimization in Discrete and Continuous Domains","metadata":[{"label":"dc.description.sponsorship","value":"This work is sponsored by the Stony Brook University Graduate School in compliance with the requirements for completion of degree."},{"label":"dc.format","value":"Monograph"},{"label":"dc.format.medium","value":"Electronic Resource"},{"label":"dc.identifier.uri","value":"http://hdl.handle.net/11401/78262"},{"label":"dc.language.iso","value":"en_US"},{"label":"dcterms.abstract","value":"This thesis includes some newly-proposed adaptive search algorithms for simulation optimization in discrete and continuous domains.     We first consider the ranking and selection problem of allocating a given simulation budget among a set of design alternatives in order to maximize the probability of correct selection. Previous research used to take static approaches to allocate certain number of simulation budget on different designs, i.e. pre-calculating the allocation plan before simulation, and among them, sequential optimal computing budget allocation (OCBA) shows the best allocation efficiency so far. Our approach, Dynamic Simulation Budget Allocation (DSBA), allocates this sampling budget dynamically by formulating this problem into an MDP framework to get a stationary index policy. Numerical results indicate that DSBA outperforms OCBA when the total budget is not large enough, while OCBA has a better efficiency when the total budget is relatively large, due to the asymptotical optimality property of OCBA.     Next, we propose an adaptive search algorithm for solving simulation optimization problems with Lipschitz continuous objective functions on compact convex domains. The algorithm combines the ideas from shrinking ball methods, surrogate model optimization, and promising area search: it employs the shrinking ball method to estimate the performance of sampled solutions to avoid multiple simulation replications on any single point, and uses the performance estimates to fit a surrogate model that iteratively approximates the response surface of the objective function to help us have better idea of the true function. The search for improved solutions at each iteration is then carried out by sampling from a promising region (a subset of the decision space) that is adaptively constructed to contain the point that optimizes the surrogate model. Under appropriate conditions, we show that the algorithm converges to the set of local optimal solutions with probability one. A computational study is also carried out to illustrate the locally convergent property and to compare its performance with some of the existing procedures."},{"label":"dcterms.available","value":"2018-06-21T13:38:46Z"},{"label":"dcterms.contributor","value":"Djuric, Petar"},{"label":"dcterms.creator","value":"Fan, Qi"},{"label":"dcterms.dateAccepted","value":"2018-06-21T13:38:46Z"},{"label":"dcterms.dateSubmitted","value":"2018-06-21T13:38:46Z"},{"label":"dcterms.description","value":"Department of Applied Mathematics and Statistics"},{"label":"dcterms.extent","value":"69 pg."},{"label":"dcterms.format","value":"Application/PDF"},{"label":"dcterms.identifier","value":"http://hdl.handle.net/11401/78262"},{"label":"dcterms.issued","value":"2017-12-01"},{"label":"dcterms.language","value":"en_US"},{"label":"dcterms.provenance","value":"Made available in DSpace on 2018-06-21T13:38:46Z (GMT). No. of bitstreams: 1\nFan_grad.sunysb_0771E_13600.pdf: 809413 bytes, checksum: 5ed076e071ca47c8080e5ad625780ccc (MD5)\n  Previous issue date:   12"},{"label":"dcterms.subject","value":"Operations research"},{"label":"dcterms.title","value":"Adaptive Search Algorithms for Simulation Optimization in Discrete and Continuous Domains"},{"label":"dcterms.type","value":"Dissertation"},{"label":"dc.type","value":"Dissertation"}],"description":"This manifest was generated dynamically","viewingDirection":"left-to-right","sequences":[{"@type":"sc:Sequence","canvases":[{"@id":"https://repo.library.stonybrook.edu/cantaloupe/iiif/2/canvas/page-1.json","@type":"sc:Canvas","label":"Page 1","height":1650,"width":1275,"images":[{"@type":"oa:Annotation","motivation":"sc:painting","resource":{"@id":"https://repo.library.stonybrook.edu/cantaloupe/iiif/2/92%2F13%2F09%2F92130940553717437056407741976733201159/full/full/0/default.jpg","@type":"dctypes:Image","format":"image/jpeg","height":1650,"width":1275,"service":{"@context":"http://iiif.io/api/image/2/context.json","@id":"https://repo.library.stonybrook.edu/cantaloupe/iiif/2/92%2F13%2F09%2F92130940553717437056407741976733201159","profile":"http://iiif.io/api/image/2/level2.json"}},"on":"https://repo.library.stonybrook.edu/cantaloupe/iiif/2/canvas/page-1.json"}]}]}]}