Virginia Tech® home

SysOptiMaL Home

Systems Optimization and Machine Learning Lab (SysOptiMaL)

SysOptiMaL People May 2024

SysOptiMaL People May 2024
SysOptiMaL People May 2024
esra toy

Esra Büyüktahtakιn Toy, Ph.D. 

Professor of Operations Research

Operations Research (OR) Program Area Lead

Department of Industrial and Systems EngineeringVirginia Tech

Director, Systems Optimization and Machine Learning (SysOptiMaL) Lab

Ph.D. in Operations Research, University of Florida, 2009
M.S. in Management Science, Lehigh University, 2007
M.S. in Industrial Engineering, Bilkent University, 2005

esratoy@vt.edu  |   540-231-0483

Dr. Esra Büyüktahtakın Toy is a Full Professor of Operations Research and Operations Research Program Area Lead in the Grado Department of Industrial and Systems Engineering at Virginia Tech, where she directs the Systems Optimization and Machine Learning Lab (SysOptiMaL). Her research develops optimization theory, models, and algorithms for sequential decision making under uncertainty, with particular emphasis on multi-stage stochastic mixed-integer optimization, decomposition and cutting-plane methods, learning-enhanced optimization, reinforcement learning, and integer programming games. Across this work, she integrates rigorous optimization methodology with machine learning (ML) and artificial intelligence (AI) to address large-scale, dynamic, and high-impact decision problems. She has graduated 9 Ph.D. students now in leading academic and industry roles and currently advises six more.
Her methodological contributions include scenario-dominance approaches for multi-stage stochastic mixed-integer programs and learning-integrated frameworks that combine optimization with deep learning and reinforcement learning. Her research spans healthcare and epidemic response, supply chains, biosecurity, ecological systems, and defense, with applications including epidemic resource allocation and logistics, invasive-species surveillance and control, decentralized resource coordination, AI-assisted optimization, and undersea surveillance and search. She has been invited to deliver the 2026 INFORMS TutORial, “Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers”, at the 2026 INFORMS Annual Meeting.
Dr. Toy’s research has received more than $3 million in external support from the National Science Foundation, Office of Naval Research, U.S. Department of Agriculture, U.S. Forest Service, and other federal, state, and interdisciplinary programs. She is the recipient of the NSF CAREER Award, the NSF EPSCoR First Award, and the INFORMS Minority Issues Forum Early Career Award. Her scholarship has received six INFORMS Best Publication Awards, along with additional publication honors and recognitions, and has been featured three times in ISE Magazine.
She has authored 49 peer-reviewed journal publications, including 27 publications in A* or A journals on the ABDC Journal Quality List, spanning stochastic optimization, mixed-integer programming, learning-enhanced optimization, game-theoretic optimization, and data-driven decision making. Her research has appeared in journals including the European Journal of Operational Research, INFORMS Journal on Computing, IISE Transactions, Computers & Operations Research, Journal of Global Optimization, and Omega. She has advised nine completed Ph.D. students and has supervised two postdoctoral researchers. Her former trainees hold academic and industry positions at institutions and organizations including Northwestern University, Oklahoma State University, SUNY Plattsburgh, Amazon, CVS, and McKinsey & Company.
Dr. Toy has also held significant leadership roles within the operations research profession. She previously served as President of the INFORMS Junior Faculty Interest Group (JFIG) and as a member of the Steering Committee for the nationwide 2024 NSF Engineering CAREER Award Workshop. She currently serves as an Associate Editor of the INFORMS Journal on Computing and Health Care Management Science, and has organized and chaired numerous INFORMS and IISE conference tracks, sessions, panels, and professional-development activities.
Select Awards and Recognition: NSF CAREER Award; NSF EPSCoR First Award; INFORMS Minority Issues Forum Early Career Award; two INFORMS ENRE Best Publication Awards in Natural Resources and Environment & Sustainability; INFORMS Computing Society Harvey J. Greenberg Research Award Honorable Mention; Dwane and Velma Wallace Award for Excellence in Research; Young Faculty Scholar Award; INFORMS Moving Spirit Award; and INFORMS Volunteer Service Award.
Research Areas: Stochastic and Risk-Averse Mixed-Integer Optimization; Multistage Stochastic Programming; Decomposition and Cutting Planes; Learning-Enhanced Optimization; Machine Learning and Artificial Intelligence; Deep Learning and Reinforcement Learning; Sequential Decision Making under Uncertainty; Integer Programming Games; Human–AI Collaboration; AI-Assisted Algorithm Design; Supply Chain and Healthcare Analytics; Epidemic Response; Biosecurity; Ecological Systems; and Defense Applications.
RECENT SYSOPTIMAL NEWS
2026 INFORMS Tutorial Forthcoming: Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers by Dr. Esra Buyuktahtakin Toy. This tutorial presents an OR/MS-centered perspective on how deep learning/AI and optimization can be integrated for complex sequential decision-making under uncertainty, with applications in healthcare, supply chains, agriculture, energy, robotics, autonomous systems, and beyond.  July 12, 2026.
SysOptiMaL ICAT Presentation: Sithuni Mimasha and SysOptiMaL member Nipun Galande presented our ICAT-funded work on Indigenous governance, community consent, and representation in LLM training at the Virginia Tech ICAT Playdate, in collaboration with Eranga Galappaththi. Watch the presentation: Rethinking the Ethical Training of AI through Indigenous Governance. September 11, 2026.
SysOptiMaL Ph.D. Defense: Congratulations to Dr. Hyunwoo Lee on successfully defending his dissertation, Multi-Agent Integer Programming Games with Non-cooperation and Cooperation. Hyunwoo, my 9th completed Ph.D. student, will join Northwestern IEMS as a postdoctoral researcher with Sanjay Mehrotra. August 5, 2026.
SysOptiMaL New Publication: Kimiya M. Jozani, Sait Tunc, Hoda Eldardiry, Nihal A. Sageer, and İ. Esra Büyüktahtakın, “Adaptive Multi-Echelon Epidemic–Supply Chain Optimization at National Scale”, has been published in IISE Transactions. The paper develops an adaptive, equity-aware epidemic–supply-chain optimization framework and scalable decomposition methods for national-scale vaccine allocation and deployment. 2026.
2026 MSOM Conference Presentation: SysOptiMaL Ph.D. student Kimiya Jozani presented “A Decision-Dependent Distributionally Robust Optimization Model for Proactive Mitigation of Infectious Disease Outbreaks” at the 2026 MSOM Conference at Harvard University, presenting our work on behavior-driven, decision-dependent DRO for epidemic mitigation. July 13, 2026.
SysOptiMaL Undergraduate Research Awards: I. Adams, A. Canuel, M. Lee, and İ. E. Büyüktahtakın, “Sustainable Timber Supply Chain Optimization”, appeared in the Refereed Proceedings of the IISE Annual Conference & Expo 2026. The student team earned 1st Place in the IISE Global Undergraduate Student Technical Paper Competition, 2nd Place in the IISE Operations Research Division Undergraduate Student Research Dissemination Competition, 1st Place at the IISE Mid-Atlantic Regional Conference, and was named a Finalist for the 2026 INFORMS Undergraduate Operations Research Prize. 2026.
2025 NeurIPS Paper & Presentation: Seung Jin Choi, Kimiya Jozani, Joshua F. Cooper, and I. Esra Büyüktahtakın Toy,Learning to Optimize at Scale: A Benders Decomposition-TransfORmers Framework for Stochastic Combinatorial Optimization,” has been accepted to the NeurIPS 2025 MLxOR Workshop on Uncertainty-Aware Decision-Making and presented at NeurIPS on December 6, 2025, San Diego, CA. 12/06/2025. 
SysOptiMaL New Paper: N. Galande, K. M. Jozani, and I. E. Büyüktahtakın Toy, “Artificial Intelligence in Supply Chain Optimization: A Systematic Review of Machine Learning Models, Methods, and Applications,” Optimization Online, 12/2025.
SysOptiMAL  New Publication: İbrahim Oğuz Çetinkaya, İ. Esra Büyüktahtakın, Parshin Shojaee, and Chandan K. Reddy, “Discovering Heuristics with Large Language Models (LLMs) for Mixed-Integer Programs: Single-Machine Scheduling,” Computers & Operations Research, 2025 (in press).
10/28/2025.
SysOptiMAL student Minseo Lee and Dr. Esra Buyuktahtakin Toy’s paper, “Mathematical Formulation of Transformer Architecture,” is selected as a finalist for the 20th INFORMS Data Mining and Decision Analytics (DMDA) Workshop Best Paper Competition (Applied Track), 10/7/2025. 
SysOptiMAL  New Publication: E. Cibaku and İ. Esra Büyüktahtakın, “An adaptive K-means and reinforcement learning (RL) algorithm to effective vaccine distribution,” Computers & Operations Research, 185 (January 2026), 107275.
9/19/2025.
Dr. Esra Toy recieves a 4-VA Collaborative Research Grant proposal on Self Learning-to-Optimize at Scale with Ferdinando Fioretto at UVA, 5/14/2025.
Dr. Toy receives a new grant award from the Virginia Department of Forestry (DOF) award on "AI-Driven Decision Optimization for the Effective Management of Wavyleaf Grass Invasions in Virginia" , 5/1/2025. 
The SysOptimaL award-winning paper on EAB surveillance and control planning is featured as a research highlight in the February 2025 edition of the INFORMS Computing Society (ICS) newsletter, 3/7/2025
SysOptiMAL advisor Dr. Buyuktahtakin Toy receives the Office of Naval Research (ONR) award on "Allocation of Surveillance and Tactical Search Assets in Undersea Warfare" totaling $623 501, 2024. Here is the story about our project with USNA: Tech and tactics unite to outsmart stealthy submarines | Virginia Tech News | Virginia Tech
Sushyanth Sridhar, M.S. student in SysOptiMaL, won first place in the 2024 ISE Graduate Student Research Poster Competition.
Kimiya Jozani Mohammadi, Ph.D. student in SysOptiMaL, received the 2024 Best Graduate Teaching Assistant Award and placed second in the 2024 ISE Graduate Student Research Poster Competition.
SysOptiMaL paper "Unlocking the Puzzle: How Healthcare Leaders Strategize Vaccine Distribution During Pandemics such as COVID-19?" has been featured in the June 2024 issue of ISE Magazine. This article stems from our SysOptiMAL IISE-T publication, “COVID-19: An Agent-Based Simulation-Optimization Approach to Vaccine Center Location and Vaccine Allocation Problem.” Read the full article here: https://lnkd.in/eiz658MN, June 2024.
Avinashh Kumar Baswapuram, former M.S. student in SysOptiMaL, received his M.S. degree with MS Thesis in August 2024 and has landed on an exciting journey as a Global Network Design Analyst at Rich’s Corporation, August 2024. Congratulations, Avinashh!
Dr. Buyuktahtakin Toy is honored to chair the 2024 INFORMS Computing Society Harvey J. Greenberg Research Award, 5/30/2024.
Hyunwoo Lee, Ph.D. student in SysOptiMaL, was a finalist at the 2024 Mixed Integer Programming Workshop Poster Presentation Competition.
SysOptiMaL member, Senior ISE student, and research assistant Josh Cooper won the 2024 VT ISE Undergraduate Research Symposium Award, 1st Place, based on the SysOptiMaL work published here: [2402.13380] Toward TransfORmers: Revolutionizing the Solution of Mixed Integer Programs with Transformers (arxiv.org), 4/23/2024.
SysOptiMAL advisor Dr. Buyuktahtakin Toy is honored to have been invited to serve as an Associate Editor for the INFORMS Journal on Computing, starting April 2024.
Dr. Buyuktahtakin Toy serves as the 2024 NSF ENG CAREER  Proposal Workshop Steering Committee, 2024.
SysOptiMAL advisor Dr. Buyuktahtakin Toy gave a keynote speech at the 2024 Invasive Species Symposium, March 15, 2024.
SysOptiMAL publication “COVID-19: An Agent-Based Simulation-Optimization Approach to Vaccine Center Location Vaccine Allocation Problem” was selected as a featured article that will appear in the June 2024 issue of the Industrial and Systems Engineer (ISE) Magazine, March 8, 2024!
New SysOptiMAL publication has just been accepted for pulication in EJOR,  Dogacan Yilmaz* and İ. Esra Büyüktahtakın, “An Expandable Machine Learning-Optimization Framework for Sequential Decision-Making,” Oct 30, 2023!
INFORMS ENRE Best Publication Award in Natural Resources, 2022, Indianapolis, IN
INFORMS Computing Society Harvey J. Greenberg Research Award, 2022, Indianapolis, IN 
News release here published by the US Forest Service Office of Communications featuring our paper (Kibis, Buyuktahtakin, and Haight et al., 2021), 2022
The ISE magazine 2022 April issue featured our IISE-T HSE article on “epidemic-vaccination-logistics”. Here is the link for the related article.
2016 INFORMS Minority Issues Forum (MIF) Early Career Award, INFORMS Conference, Nov 2016, Nashville, TN 
2016 INFORMS Moving Spirit Award, INFORMS Conference, Nov 2016, Nashville, TN 
Engineering professor wins National Science Foundation award, Wichita State News, Feb 29, 2016
USDA AFRI Award, USDA.gov, March 1, 2016
Professors’ research helping Kansas ranchers with invasive weeds,  Wichita State News, Aug. 16, 2016