[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124760-en":3,"doc-seo-124760-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124760,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","An Expandable Machine Learning-Optimization Framework to Sequential Decision-Making","An integrated prediction-optimization (PredOpt) framework is proposed to solve sequential decision-making problems efficiently by predicting binary decision variables embedded in optimal solutions. Key challenges of sequential dependence, infeasibility, and generalization are addressed using recurrent neural networks with a sliding-attention window. An attention-based encoder-decoder with infeasibility elimination and generalization learns high-quality feasible solutions for time-dependent combinatorial optimization, then fixes predictions in mixed-integer programming for rapid solution via a commercial solver.","arXiv :2311 .06972v1 [ cs .LG] 12 Nov 2023  \nAn Expandable Machine Learning-Optimization Framework to Sequential  \nDecision-Making  \nDogacan Yilmaza , ˙I . Esra B¨uy¨uktahtakınb,∗  \na Department of Mechanical and Industrial Engineering, New Jersey Institute of Technology, Newark, NJ 07102,  \nUSA  \nb Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA 24061, USA  \nAbstract  \nWe present an integrated prediction-optimization (PredOpt) framework to efficiently solve sequential decision-making problems by predicting the values of binary decision variables in an optimal solution. We address the key issues of sequential dependence, infeasibility, and generalization in machine learning (ML) to make predictions for optimal solutions to combinatorial problems. The sequential nature of the combinatorial optimization problems considered is captured with recurrent neural networks and a sliding-attention window. We integrate an attention-based encoder-decoder neural network architecture with an infeasibility-elimination and generalization framework to learn high-quality feasible solutions to time-dependent optimization problems. In this framework, the required level of predictions is optimized to eliminate the infeasibility of the ML predictions. These predictions are then fixed in mixed-integer programming (MIP) problems to solve them quickly with the aid of a commercial solver. We demonstrate our approach to tackling the two wellknown dynamic NP-Hard optimization problems: multi-item capacitated lot-sizing (MCLSP) and multi-dimensional knapsack (MSMK) . Our results show that models trained on shorter and smallerdimensional instances can be successfully used to predict longer and larger-dimensional problems. The solution time can be reduced by three orders of magnitude with an average optimality gap below 0 . 1% . We compare PredOpt with various specially designed heuristics and show that our framework outperforms them. PredOpt can be advantageous for solving dynamic MIP problems that need to be solved instantly and repetitively.  \nKeywords:  \n(R) Machine learning, encoder-decoder, capacitated lot-sizing, knapsack, combinatorial optimization  \nThe final version of this article has been accepted for publication in European Journal of Operational Research and can be accessed via [https://doi.org/10.1016/j.ejor.2023.10.045](https://doi.org/10.1016/j.ejor.2023.10.045) .  \n∗ Corresponding author  \nEmail addresses: [dy234@njit.edu](dy234@njit.edu) (Dogacan Yilmaz), [esratoy@vt.edu](esratoy@vt.edu) (˙I . Esra B¨uy¨uktahtakın)  \n1. Introduction  \nThe goal of this paper is to contribute to bridging the gap between two traditionally distinct research areas, Operations Research (OR) and Machine Learning (ML), to solve NP-hard sequential decision-making problems. OR is a discipline that aims to find the best decisions for complex problems through mathematical modeling and optimization, while ML focuses on learning from the data without explicitly programming it. In this paper, we tackle a very hard category of OR problems known as combinatorial optimization problems by innovatively combining a machine translation learning framework with an optimization-learning framework.  \nOur objective is to substantially reduce the solution times of such combinatorial problems while providing high-quality feasible solutions, which could be very useful in practical applications. Inmost industrial settings, such as finance, health, energy, and manufacturing systems, OR problems with the same structures are repeatedly solved with different parameters. For such settings, a reduced solution time can provide an immense advantage to decision-makers. In this study, we present an expandable framework based on a sequence-to-sequence neural machine translation system to solve sequentially dependent optimization problems with all feasible predictions, which are either optimal or very close to optimal.  \nYilmaz and B¨uy¨uktahtakın (2023b) present one","cbCaicB9chENkMhb","https://ap.wps.com/l/cbCaicB9chENkMhb","pdf",1415575,1,35,"English","en",105,"# Introduction\n## Bridging Operations Research and Machine Learning\n## Expandable PredOpt sequence-to-sequence approach","[{\"question\":\"What is the PredOpt framework designed to do?\",\"answer\":\"PredOpt combines machine learning predictions with optimization to solve sequential decision-making problems efficiently by predicting binary decision variables in an optimal solution.\"},{\"question\":\"How does the framework handle sequential dependence and infeasibility?\",\"answer\":\"It captures sequential structure with recurrent neural networks plus a sliding-attention window, and uses an attention-based encoder-decoder together with an infeasibility-elimination and generalization mechanism.\"},{\"question\":\"How are the ML predictions used to obtain final solutions?\",\"answer\":\"The learned predictions are fixed as constraints in mixed-integer programming (MIP) models, enabling fast solving using a commercial solver.\"}]","An Expandable Machine Learning-Optimization Framework to Sequential Decision-Making | PDF",1785894348,88,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"an-expandable-machine-learning-optimization-framework-to-sequential-decision-making","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/an-expandable-machine-learning-optimization-framework-to-sequential-decision-making/124760/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the PredOpt framework designed to do?","Question",{"text":75,"@type":76},"PredOpt combines machine learning predictions with optimization to solve sequential decision-making problems efficiently by predicting binary decision variables in an optimal solution.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the framework handle sequential dependence and infeasibility?",{"text":80,"@type":76},"It captures sequential structure with recurrent neural networks plus a sliding-attention window, and uses an attention-based encoder-decoder together with an infeasibility-elimination and generalization mechanism.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the ML predictions used to obtain final solutions?",{"text":84,"@type":76},"The learned predictions are fixed as constraints in mixed-integer programming (MIP) models, enabling fast solving using a commercial solver.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]