Find Academic Supervisors

Bo DaiView profile

Assistant Professor

• Reinforcement Learning
• Machine Learning
• Data-Driven Decision Making
• +3 more

Bo Dai is an Assistant Professor at the School of Computational Science and Engineering, Georgia Institute of Technology, and a Staff Research Scientist at Google DeepMind. His research focuses on Agent AI, Generative Models, and Representation Learning, aiming to create decision-making agents through world modeling. He holds a Ph.D. from Georgia Tech (2013–2018) and previously worked at Google Brain. Dai has authored numerous influential papers in top conferences like NeurIPS, ICML, and ICLR, and received the AISTATS Best Paper Award (2016). Education: Ph.D., School of Computational Science and Engineering, Georgia Tech (2013–2018) Research Interests: Reinforcement Learning and Representation Learning for decision-making agents Generative Models and their integration with Agent AI Provable and scalable algorithms for real-world applications His work bridges theory and practice, emphasizing spectral representations and provable guarantees in complex systems. Key Article Trends: His recent work emphasizes scalable spectral methods for multi-agent systems, diffusion policies, and representation-based techniques in reinforcement learning. He also explores LLM alignment and sim-to-real transfer learning. Awards: AISTATS Best Paper Award (2016) NeurIPS Workshop Best Paper (2017) Ross Fellowship (2011–2012) Advising & Grants: Supervises 6 current Ph.D. and M.S. students. Active in organizing workshops on reinforcement learning and serves as an Area Chair for top conferences. Labs & Software: Leads development of Representation-based Reinforcement Learning and Repr-Control toolboxes for nonlinear control and stochastic systems.

• Operations Research
• Machine Learning
• Optimization under Uncertainty
• +4 more

Minseok Ryu is an Assistant Professor at the School of Computing and Augmented Intelligence, Arizona State University (ASU). He holds a Ph.D. in Industrial & Operations Engineering from the University of Michigan (2020). Prior to ASU, he was a postdoctoral appointee at Argonne National Laboratory’s Mathematics and Computer Science Division. His research focuses on optimization methodologies for decentralized and stochastic decision-making distributed algorithms for machine learning and operations research applications in healthcare systems and energy grids Teaching responsibilities include courses on applied deterministic operations research (IEE 574), optimization (IEE 622), and research practicums (IEE 792). His work emphasizes computational challenges in decision-making under uncertainty, with recent projects addressing nurse staffing optimization, federated learning frameworks (e.g., APPFL/APPFLX), and resilient power grid systems. He has no recorded academic awards but actively contributes to open-source software and cross-disciplinary research collaborations. Research interests bridge theory and practice, targeting social goods through optimization techniques like distributionally robust optimization, federated learning, and heuristic algorithms for energy and healthcare systems.

Fatma Kılınç-KarzanView profile

Associate Professor

• Mathematical Optimization
• Convex Optimization
• Non-convex Optimization
• +7 more

Fatma Kılınç-Karzan is an Associate Professor of Operations Research at Carnegie Mellon University's Tepper School of Business, with a courtesy appointment as Associate Professor of Computer Science. She is also affiliated with the Algorithms Combinatorics and Optimization (ACO) PhD Program and was a Visiting Scientist at Berkeley's Simons Institute for the Theory of Computing during Fall 2017. Her educational background includes a PhD from Georgia Institute of Technology's H. Milton Stewart School of Industrial & Systems Engineering with a minor in Mathematics, supervised by Prof. Arkadi Nemirovski. She earned her B.S. and M.S. degrees from the Industrial Engineering Department of Middle East Technical University with a minor in Information Systems. Dr. Kılınç-Karzan's research spans mathematical optimization with emphasis on convex and non-convex optimization theory, algorithms, and applications. Her work bridges theoretical foundations with practical implementations in optimization under uncertainty (robust optimization, chance constraints, distributionally robust optimization), machine learning (preference learning from limited data), and business analytics. She develops foundational theory for large-scale optimization problems with applications in decision making under uncertainty and high-dimensional statistical inference. Analysis of her recent publications reveals a strong focus on convex hull characterizations, semidefinite programming relaxations, distributionally robust optimization, and online convex optimization frameworks. Her work demonstrates increasing integration of optimization theory with machine learning applications, particularly in developing data-driven approaches for decision making under uncertainty. NSF CAREER Award (2015) INFORMS Optimization Society Young Researcher Prize (2015) INFORMS Junior Faculty Interest Group (JFIG) Best Paper Award (2014) BP Junior Faculty Chair (2014-2015) Faculty Giving Chair (2012-2013) Wimmer Fellowship (2012-2013) Dr. Kılınç-Karzan has successfully mentored numerous PhD students who have received prestigious awards, including the 2021 INFORMS Optimization Society Best Student Paper (1st prize) and multiple honorable mentions. Her research has been supported by significant grants including an NSF CAREER Award, an ONR grant (with S. Küçükyavuz), and an AFOSR grant. She serves on editorial boards for Mathematical Programming, Operations Research, Mathematics of Operations Research, and other leading journals, and has held leadership positions in professional societies including the Mathematical Optimization Society and INFORMS Computing Society. Through her affiliations with CMU's Tepper School, Computer Science Department, and ACO Program, she collaborates across disciplines to advance optimization theory and its applications. Her professional service includes committee chair roles for major INFORMS competitions and program committee leadership for international optimization conferences.

Nagi GebraeelView profile

Professor

• Predictive Analytics
• Machine Learning
• Prognostics and Health Management
• +5 more

Professor Nagi Gebraeel serves as the Georgia Power Early Career Professor in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Institute of Technology, where his research integrates predictive analytics, machine learning, and optimization for industrial IoT applications. His work focuses on real-time equipment diagnostics, prognostics, and operational decision-making in critical infrastructure systems. Education: Ph.D. in Industrial Engineering (2003), Purdue University M.S. in Industrial Engineering (1998), Purdue University Research Focus: Dr. Gebraeel develops statistical learning algorithms for IoT-enabled maintenance, repair, and operations (MRO), with emphasis on federated learning frameworks for distributed fault diagnosis and cybersecurity protection against Industrial Control System (ICS) attacks. His research spans manufacturing, power generation, and deep space habitats through NASA's HOME Space Technology Research Institute, where he pioneers self-aware habitat systems. Recent work addresses data heterogeneity in high-consequence industrial environments using causal-informed analytics. Publication Trends: His 2024-2025 publications demonstrate a strong trajectory toward distributionally robust optimization for maintenance logistics, federated learning architectures for distributed fault diagnosis, and prognostics for complex systems like offshore wind farms and industrial robots. Key themes include handling imbalanced data in fault diagnosis, state-space representations for interdependent systems, and cybersecurity integration in manufacturing networks. Awards and Recognition: NSF CAREER Award (2007) SAE Aircraft Electrical Power System Recognition Award (2008) SAE Materials Modeling and Testing Recognition Award (2006) IEEE-AUTOTESTCON Certificate (2006) Fellow of the Institute of Industrial and Systems Engineers Advising and Funding: Dr. Gebraeel mentors doctoral students including Michael Ibrahim (2025 IISE Best Student Paper winner), Heraldo Rozas (now Assistant Professor at University of Chile), Ayush Mohanty, and Nazal Mohamed. He secured a $500,000 NSF grant in August 2025 for AI-driven cybersecurity in distributed manufacturing networks and leads NASA-funded research on deep space habitat systems. His work bridges academic research with industry applications through Georgia Tech's Strategic Energy Institute collaborations. Research Infrastructure: He directs the Analytics and Prognostics Systems laboratory at Georgia Tech's Manufacturing Institute and leads the Predictive Analytics and Intelligent Systems (PAIS) research group. Previously, he served as associate director of Georgia Tech's Strategic Energy Institute (2014-2019), fostering data science applications in energy systems.

Eric V. MazumdarView profile

Assistant Professor

• Machine Learning
• Economics
• Optimization
• +4 more

Eric V. Mazumdar is an Assistant Professor at the California Institute of Technology (Caltech), jointly appointed in the departments of Computing and Mathematical Sciences and Economics. He holds a B.S. from MIT (2015) and a Ph.D. from UC Berkeley (2021), co-advised by Michael Jordan and Shankar Sastry. His research bridges machine learning and economics, focusing on deploying algorithms into societal systems through theoretical and practical lenses. Key areas include strategic classification, multi-agent reinforcement learning, and distributionally robust optimization, with applications in healthcare, online markets, and intelligent infrastructure. Education: B.S., Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 2015 Ph.D., Electrical Engineering and Computer Science, University of California, Berkeley, 2021 Research Interests: Mazumdar’s work emphasizes understanding learning algorithms in strategic environments, including min-max optimization, game theory, and multi-agent systems. He explores how algorithms interact with human and algorithmic agents in dynamic systems, with practical applications in healthcare delivery, e-commerce, and autonomous systems testing. Awards: NSF CAREER Award (2023) Simons Institute Research Fellowship in Learning in Games Grants & Funding: Supported by NSF, DARPA, Amazon, and other organizations. His NSF CAREER grant focuses on strategic interactions in societal-scale systems. Teaching: Courses include Networks: Structure & Economics (CMS/CS/EE/IDS 144) and Topics in Learning and Games (CMS/Ec 248). At UC Berkeley, he contributed to courses like Data, Inference, and Decisions (DS 102). Students & Postdocs: Current students: Lauren Conger, Tinashe Handina, Yizhou Zhang Postdocs: Zaiwei Chen, Laixi Shi, Kishan Panaganti (co-advised with Adam Wierman)

• Machine Learning
• Statistical Learning Theory
• Optimization
• +3 more

Professor Yiming Ying is a faculty member in the Faculty of Science at the University of Sydney, where he joined in December 2023. Previously, he held tenured positions at SUNY Albany (Departments of Mathematics & Statistics and Computer Science) and was a Lecturer at the University of Exeter. He completed his PhD in Mathematics at Zhejiang University (2002) and postdoctoral training at CityU Hong Kong, UCL, and University of Bristol. Research Focus His research spans statistical learning theory, optimization algorithms, trustworthy AI, and data science mathematics. Key applications include cancer informatics for early detection. His work aligns with Faculty research strengths in Data and Decisions and Decision-Making for a Sustainable Future. Recent Research Trends Analysis of recent publications shows strong focus on theoretical foundations of machine learning: differential privacy, fairness algorithms, optimization methods for AUC maximization, generalization guarantees, and robust learning techniques for adversarial settings and biological data. Awards and Honors SUNY Chancellor’s Award for Excellence (2023) University at Albany Presidential Research Award (2022) University of Exeter Merit Award (2012) Grants and Advising Significant funding includes current ARC DP250101359 (2025-2028) and multiple past NSF grants. He founded the UALBANY Machine Learning Group and currently advises PhD student Peilin LIU on operator learning.

• Machine Learning
• Artificial Intelligence
• Data Science
• +7 more

Pan Xu is a tenure-track assistant professor with joint appointments in the Department of Biostatistics & Bioinformatics, Department of Computer Science, and Department of Electrical & Computer Engineering at Duke University. Previously, Xu was a Postdoctoral Scholar Research Associate at Caltech's Department of Computing and Mathematical Science and earned a Ph.D. in Computer Science from UCLA. Xu's research focuses on developing computationally- and data-efficient machine learning algorithms with strong empirical performance and theoretical guarantees. Xu's research interests center around Machine Learning with broad applications in Artificial Intelligence, Data Science, Optimization, Reinforcement Learning, and High Dimensional Statistics. The research specifically targets real-world problems in Bioinformatics and Healthcare, with recent work emphasizing distributionally robust decision making, efficient exploration strategies, and multi-agent systems. Xu has developed novel algorithms that address the challenges of exploration in sequential decision making and robustness to distributional shifts between training and deployment environments. Xu's recent publications demonstrate a strong trend toward developing theoretically grounded yet practical algorithms for reinforcement learning and bandit problems, with particular emphasis on distributionally robust methods, efficient exploration techniques, and applications to healthcare. The work spans both theoretical analysis (providing minimax optimal regret bounds) and practical implementations (validated on benchmarks like Atari games and real healthcare datasets). Whitehead Scholar award from Duke University School of Medicine (2023) Best Paper Award at ACM FAccT 2023 for Queer In AI paper PIMCO Postdoctoral Fellowship in Data Science (2022) TMLR Featured Certification (2023) NSF award on approximate sampling based exploration (2023) Xu actively mentors multiple Ph.D. students across Duke's Biostatistics & Bioinformatics, Computer Science, and Electrical & Computer Engineering programs, with several alumni now pursuing doctoral studies at top institutions. The research group has secured competitive funding including an NSF award for approximate sampling based exploration for sequential decision making. Xu serves as an action editor for TMLR and as an area chair for major conferences including ICML, NeurIPS, AAAI, ICLR, and AISTATS. Xu leads a dynamic research group focused on sequential decision making, with projects spanning theoretical algorithm development, implementation of practical systems, and applications to healthcare and bioinformatics. The group maintains active collaborations across Duke's medical and engineering schools, with recent work applying machine learning to epidemic forecasting during the pandemic.

Tatsunori HashimotoView profile

Assistant Professor

• Artificial Intelligence
• Machine Learning
• Natural Language Processing
• +3 more

Tatsunori Hashimoto is an Assistant Professor of Computer Science at Stanford University, specializing in artificial intelligence, machine learning, and natural language processing. His research focuses on developing robust and ethical language models, addressing challenges in bias mitigation, fairness, and transparency. He leads projects like the Stanford Alpaca, exploring instruction-following models and their societal impacts. Key research interests include generative models, AI ethics, and privacy-preserving techniques. His recent work examines language model behaviors, security risks, and the societal implications of AI systems. Notable contributions include frameworks for auditing language models, improving factual accuracy, and reducing disparities in speech recognition. His publications highlight advancements in long-context processing, few-shot learning, and automated benchmarking. He emphasizes practical applications of AI while addressing dual-use concerns and ensuring alignment with human values.

Soroosh ShafieeView profile

Assistant Professor

• Optimization under Uncertainty
• Robust Optimization
• Optimal Transport
• +3 more

Soroosh Shafiee is an Assistant Professor in the School of Operations Research and Information Engineering at Cornell University since July 2023. Before joining Cornell, he held postdoctoral positions at the Tepper School of Business (Carnegie Mellon University) and the Automatic Control Laboratory (ETH Zurich). He earned a B.Sc. and M.Sc. in Electrical Engineering from the University of Tehran and a Ph.D. in Operations Research from École Polytechnique Fédérale de Lausanne (EPFL). His research focuses on optimization under uncertainty, robust optimization, optimal transport, and their applications in machine learning and finance. Specific interests include designing algorithms for data-driven optimization, analyzing statistical and computational complexity, and exploring nonconvex optimization structures. Swiss National Science Foundation Early PostDoc Mobility Fellowship (2020) PhD Thesis Distinction Award, EPFL (2020) His work bridges theoretical foundations with practical applications, contributing to areas such as distributionally robust optimization, Wasserstein-based methods, and scalable algorithm development. His research has been published in top venues like Journal of Machine Learning Research and Operations Research .

Ming CaoView profile

Professor

• Multi-agent systems
• Autonomous Robots
• Complex Systems and Networks
• +4 more

Ming Cao is a Full Professor at the University of Groningen (Netherlands), holding positions in the Department of Discrete Technology and Production Automation, the Engineering and Technology Institute Groningen, and serving as Chair of the Jantina Tammes School of Digital Society, Technology and AI. His academic roles include Director of the Jantina Tammes School and membership in prestigious organizations such as the International Federation of Automatic Control (IFAC) and the European Commission’s DG CNECT. Cao’s research focuses on multi-agent systems, autonomous robotics, complex networks, and cooperative control, with applications in robotics, epidemic modeling, and biomimetic sensors. Education: PostDoc in Mechanical Engineering from Princeton University (2008), PhD in Electrical Engineering from Yale University (2007). Research Interests: Multi-agent systems, distributed decision-making, cooperative control, robotic teams, seal whisker-inspired flow sensing, and privacy-preserving control systems. Recent Trends in Articles: Recent work emphasizes co-evolutionary dynamics in social-technical systems, privacy in control systems, and biomimetic robotics. Key topics include feedback mechanisms in cooperation, hypergraph-based epidemic models, and seal whisker mechanics for underwater sensing. Awards: European Control Award (2016), Manfred Thoma Medal (2017), ERC Grant (2012). Grants: Vidi Grant from NWO (2015) for agent coordination research. Labs/Teams: Jan C. Willems Center for Systems and Control, Research Center for Data Science and Systems Complexity (DSSC). Active in editorial roles for journals like Artificial Life and Robotics and the SIAM Journal on Control and Optimization .

Rohit KannanView profile

Assistant Professor

• Learning + Optimization
• Optimization Under Uncertainty
• Global Optimization
• +2 more

Rohit Kannan is an Assistant Professor in the Grado Department of Industrial and Systems Engineering at Virginia Tech. He holds a Ph.D. and M.S. in Chemical Engineering from MIT and a B.Tech. from IIT Madras. His research focuses on integrating machine learning with global optimization and optimization under uncertainty, emphasizing energy systems applications. Previous roles include postdoc positions at Los Alamos National Laboratory and the Wisconsin Institute for Discovery. Education: Ph.D., Chemical Engineering, Massachusetts Institute of Technology, 2018 M.S., Chemical Engineering Practice, MIT, 2014 B.Tech., Chemical Engineering, IIT Madras, 2012 Research Interests: Global optimization, optimization under uncertainty, computational optimization, energy systems, and machine learning integration. Recent Highlights: Recipient of the Excellence in Teaching Spotlight Award (2024) Lead researcher in stochastic optimization and energy systems (e.g., hybrid polygeneration systems) Developed algorithms for chance-constrained nonlinear programs and distributionally robust optimization Service & Leadership: Elected Vice-Chair of Global Optimization, INFORMS Optimization Society (2025–2026) Reviewer for top journals like Operations Research and Mathematical Programming Advisor to ISE InclusiveVT and Graduate Admissions Committee Labs & Collaborations: Directs a research group advancing optimization and machine learning for energy and engineering systems. Active in interdisciplinary projects with LANL and UW-Madison.

David Alan GoldbergView profile

Associate Professor

• Applied Probability
• Operations Research
• Stochastic Processes
• +7 more

David Alan Goldberg is an Associate Professor in the School of Operations Research and Information Engineering (ORIE) at Cornell University, part of Cornell Engineering. He joined Cornell in 2017 and previously held the A. Russel Chandler III Associate Professorship at Georgia Tech’s Industrial and Systems Engineering department. Goldberg earned his Ph.D. in Operations Research from MIT (2011) and a B.S. in Computer Science from Columbia University (2006). Education: B.S. in Computer Science, Columbia University (2006) Ph.D. in Operations Research, MIT (2011) Research Interests: Goldberg’s work focuses on applied probability and stochastic processes, including optimal stopping, inventory and queueing models, combinatorial optimization, and robust optimization. He develops algorithms and insights for complex systems, addressing challenges like the curse of dimensionality. His research spans applications in data science, operations research, and stochastic modeling. Notable contributions include distributionally robust inventory control and high-dimensional decision-making frameworks. Awards and Honors: 2025 Community-Engaged Practice and Innovation Award (David M. Einhorn Center) 2023 Sunny Yau ’72 Teaching Award (Cornell) 2019 INFORMS Applied Probability Society Best Publication Award 2015 NSF CAREER Award Multiple INFORMS Nicholson Student Paper Competitions (First Place, 2019 & 2015) Teaching and Service: Goldberg leads Cornell ORIE’s undergraduate research program, connecting students to real-world applications of OR and data science. He teaches courses in probability modeling, stochastic models, and academic skills for PhD students. He chairs the INFORMS Applied Probability Society and serves on editorial boards for Operations Research and Stochastic Systems . At Cornell, he advises the Undergraduate ORIE Society and directs undergraduate studies in ORIE. Labs & Collaborations: Goldberg’s research integrates theoretical rigor with practical applications, often involving collaborations across disciplines. His work bridges operations research, statistics, and computer science to address modern challenges in inventory systems, queueing networks, and decision-making under uncertainty.

Anqi LiuView profile

Assistant Professor

• Machine Learning
• Trustworthy AI
• Distributionally Robust Learning
• +7 more

Anqi Liu is an Assistant Professor in the Department of Computer Science at the Whiting School of Engineering, Johns Hopkins University. She maintains significant affiliations with the Johns Hopkins Mathematical Institute for Data Science (MINDS) and the Johns Hopkins Institute for Assured Autonomy (IAA), while also collaborating extensively with the Center for Language and Speech Processing (CLSP) and the Laboratory for Computational Sensing and Robotics (LCSR). Her research focuses on developing principled machine learning algorithms for building reliable, trustworthy, and human-compatible AI systems in real-world applications. Key research areas include: Distributionally robust learning under covariate shift Uncertainty quantification for AI safety and fairness Safe exploration in control systems Fair machine learning under distribution shift Active learning under label shift Dr. Liu's work addresses critical challenges in high-stakes AI applications where reliability, safety, and societal impact are paramount. Her methods ensure AI systems remain robust to changing data environments, provide accurate uncertainty estimates, and incorporate human preferences in interactions. Analysis of her recent publications reveals a strong trajectory in trustworthy AI research with significant contributions to distribution shift handling, uncertainty quantification techniques, and safe decision-making frameworks. Her work bridges theoretical foundations with practical applications across healthcare, robotics, and social media analysis. Amazon Research Award Dr. Liu actively mentors eight PhD students and teaches specialized courses on Machine Learning for Trustworthy AI and standard Machine Learning at Johns Hopkins University, preparing the next generation of researchers to address critical challenges in AI safety and reliability.

Jim LuedtkeView profile

Professor

• Operations Research
• Stochastic Optimization
• Integer Programming
• +2 more

Jim Luedtke is a Professor in the Department of Industrial and Systems Engineering at the University of Wisconsin-Madison. His research focuses on operations research, integer programming, and stochastic optimization methods for solving discrete and uncertain decision problems. Educational Background: BS in Industrial Engineering from University of Wisconsin-Madison MS in Operations Research from Georgia Institute of Technology PhD in Industrial and Systems Engineering from Georgia Institute of Technology Postdoctoral Research at IBM T.J. Watson Research Center His work spans applications in power systems optimization, healthcare analytics, and network design, with particular emphasis on developing cutting-edge algorithms for chance-constrained and multistage stochastic programming problems. Recent publications demonstrate strong focus on Benders decomposition techniques, Lagrangian dual methods, and distributionally robust optimization frameworks. Scientific Awards: NSF CAREER Award (2010) for "Risk Management via Stochastic Programming: Models, Computation, and Applications"

• Risk Analysis
• Resilience Engineering
• Optimization Under Uncertainty
• +7 more

Dr. Yi-Ping Fang is an Assistant Professor at the EDF Chair SSEC with a joint appointment at the Industrial Engineering Laboratory, CentraleSupélec, Université Paris-Saclay, France. His research focuses on computational methods for risk, vulnerability, and resilience analysis of critical infrastructures including smart grids, electrified transportation, and interdependent lifeline systems. Risk Analysis Resilience Engineering Optimization Under Uncertainty Game Theory Applications His work applies advanced techniques like distributionally robust optimization, POMDP modeling, and interdependency analysis to enhance infrastructure resilience against climate change, natural hazards, and intentional attacks. Publications demonstrate expertise in hybrid optimization algorithms, stochastic modeling, and network vulnerability assessment. Recent trends include: Smart grid resilience enhancement Uncertainty quantification in infrastructure systems Multi-stage decision modeling Game-theoretic approaches for interdependent networks Integration of deep learning for dynamic system prediction