جست‌وجوی استاد و پژوهشگر

Moïse Blanchardمشاهده پروفایل

استادیار

• Machine Learning Theory
• Online Algorithms
• Optimization
• +۴ مورد دیگر

Moïse Blanchard is an Assistant Professor and Tennenbaum Early Career Professor at the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Institute of Technology, having joined in August 2025. Previously, he was a Postdoctoral Fellow at Columbia University Data Science Institute. His academic journey includes a Ph.D. in Operations Research from MIT (2024), and M.Sc. and B.Sc. degrees in Applied Mathematics from École Polytechnique. Blanchard's research focuses on the intersection of machine learning theory, statistics, and optimization. His work addresses fundamental questions in universal learning, online algorithms, and convex optimization under memory constraints. His research program explores learnability under minimal assumptions, query complexity/memory tradeoffs, and decision-making in adversarial environments. This work has significant implications for theoretical computer science, operations research, and statistical learning theory. His publications reveal a strong emphasis on foundational aspects of learning theory and optimization. Recent work demonstrates expertise in universal learning frameworks, memory-constrained optimization, and probabilistic analysis of combinatorial problems. His research often bridges theoretical computer science with practical optimization challenges, particularly in contexts where traditional i.i.d. assumptions don't hold. Columbia DSI postdoctoral fellowship, 2024 INFORMS Transportation Science & Logistics (TSL) best student paper award, 2023 Air Force Office of Scientific Research Grant (AFOSR), with Prof. Patrick Jaillet, 2023 COLT 2022 Best student paper runner-up Bronze medal, Alibaba Global Mathematics Competition, 2022 Blanchard has received significant research funding including an Air Force Office of Scientific Research Grant. His work has been recognized with multiple prestigious awards, including the INFORMS TSL best student paper award for his research on the k-Traveling Salesman Problem. His extensive publication record in top venues demonstrates a strong research trajectory with impactful contributions to theoretical machine learning and optimization.

Lawrence M. Weinمشاهده پروفایل

استاد

• Operations Management
• Public Health
• Homeland Security
• +۵ مورد دیگر

Lawrence M. Wein is the Jeffrey S. Skoll Professor of Management Science at Stanford University's Graduate School of Business, where he also serves as Senior Associate Dean of Academic Affairs. He holds a PhD in Operations Research from Stanford (1988) and has taught operations management at MIT (1988–2002) and Stanford since 2003. His research spans operations management, public health, and homeland security, with notable contributions to HIV therapy optimization, bioterror response logistics, and forensic science innovations. His academic roles include Senior Fellow at Stanford’s Center for International Security and Cooperation, and editorial leadership as Editor-in-Chief of Operations Research (2000–2005). Notable awards include the Kimball Medal, Lanchester Prize, and membership in the National Academy of Engineering. Research interests emphasize applying operations research to real-world challenges, such as optimizing radiation detection systems, analyzing sexual assault kit backlogs, and improving ballistic imaging techniques. His work bridges theoretical models with practical policy, impacting areas like healthcare, counterterrorism, and criminal justice. Key contributions include developing the workload regulating release policy in semiconductor manufacturing, influencing U.S. smallpox vaccination strategy, and advancing mathematical models for cancer treatment and pandemic influenza control. His recent focus includes forensic genetic genealogy and crime-solving technologies. Grants and collaborations span industries, governments, and academic institutions, reflecting interdisciplinary impact. His teaching includes courses on operations management, stochastic networks, and homeland security applications.

Tianyi Linمشاهده پروفایل

استادیار

• Optimization
• Game Theory
• Machine Learning
• +۳ مورد دیگر

Tianyi Lin serves as an Assistant Professor in the Department of Industrial Engineering and Operations Research (IEOR) at Columbia Engineering, Columbia University, a position he assumed in 2024. He holds dual affiliations as a verified Data Science Institute (DSI) Member and an Affiliated Member of both the Financial and Business Analytics Center and the Foundations of Data Science Center. His academic credentials include: Ph.D. in Electrical Engineering and Computer Science, UC Berkeley Postdoctoral Researcher, Laboratory for Information & Decision Systems (LIDS), MIT (2023-2024) M.S. in Operations Research, UC Berkeley M.S. in Pure Mathematics and Statistics, University of Cambridge B.S. in Mathematics, Nanjing University Dr. Lin's research spans optimization theory , game-theoretic models , and machine learning algorithms , with emphasis on nonconvex minimax problems , variational inequalities , and data science applications . His work bridges theoretical guarantees with practical implementations in high-dimensional settings, particularly focusing on convergence properties and computational efficiency in complex systems. Analysis of his 15 most recent publications (2022-2025) reveals dominant themes in high-order optimization methods , no-regret learning in games , and optimal transport algorithms . His contributions demonstrate consistent innovation in developing doubly optimal algorithms for monotone games, spectral regularization techniques for policy optimization, and structure-driven approaches for nonconvex problems, reflecting strong interdisciplinary connections between operations research, computer science, and applied mathematics. No scientific awards or honors were documented in the provided source material. Information regarding student advising and research grants remains unspecified in the current documentation, though his center affiliations suggest active participation in collaborative research initiatives. Dr. Lin maintains significant interdisciplinary engagement through his affiliations with Columbia's Data Science Institute and specialized research centers, positioning his work at the intersection of theoretical optimization and real-world data science applications.

James Smithمشاهده پروفایل

استاد

• Decision Analysis
• Management Science
• Operations Research
• +۴ مورد دیگر

James Smith is a Professor in Decision Science at the Tuck School of Business, Dartmouth College. He holds a PhD (1990), MS (1986), and BS (1984) from Stanford University. Education: PhD, MS, BS - Stanford University His research focuses on Decision Analysis , Operations Research , and Stochastic Optimization , with applications in energy systems, medical decision-making, and technology adoption. Recent work includes dynamic programming approaches to energy systems under uncertainty and information relaxation techniques in stochastic dynamic programs. Key publication trends: 15 most recent articles span 2025–2004, emphasizing stochastic dynamic programming , resource allocation , and risk evaluation across energy, finance, and public health domains. Scientific awards: Jack Byrne Distinguished Professor in Decision Science He has collaborated extensively in Operations Research and Management Science journals, with notable coauthors like David Brown, Canan Ulu, and Robert Winkler. His work addresses theoretical and applied problems in portfolio management, commodity pricing, and sequential decision modeling.

• Reinforcement Learning
• Bandit Algorithms
• Learning Theory
• +۴ مورد دیگر

Claire Vernade is a Group Leader at the University of Tübingen within the Cluster of Excellence Machine Learning for Science. She holds an Emmy Noether award (2022) and an ERC Starting Grant (2024) for her projects FoLiReL and ConSequentIAL , focusing on theoretical reinforcement learning and non-stationary environments. Education: PhD from Telecom ParisTech (2017) Post-doctoral researcher at University of Magdeburg (2018) Her research bridges sequential decision making, bandit problems, and reinforcement learning theory. Recent work explores lifelong learning, distributional RL, and game-theoretic approaches to PCA, emphasizing mathematical rigor and algorithmic innovation. Recent publications highlight trends in non-stationary RL , continual learning , and bandit algorithms with complex feedback structures. Key subfields include meta-learning, adaptive control, and theoretical guarantees in dynamic programming. Scientific Awards: Emmy Noether Award (2022) ERC Starting Grant (2024) Outstanding Paper Award & Oral Presentation, ICLR (2021) She mentors PhD and master's students in theoretical machine learning, with current advisees including Nicolas Nguyen, Onno Eberhard, and Ziyad Sheebaelhamd. Her lab actively recruits candidates in bandit algorithms and RL theory through the IMPRS-IS and ELLIS doctoral programs. Claire co-leads diversity initiatives like Tübingen Women in Machine Learning and Women in Learning Theory, advocating for inclusivity in AI research. She has organized workshops at ICML and EWRL, and contributed to union activism in the tech industry.

• Tsetlin Machines
• Reinforcement Learning
• Machine Learning
• +۳ مورد دیگر

Xuan Zhang is an Associate Professor at the Department of Information and Communication Technology, University of Agder. His research focuses on Tsetlin Machines, learning automata, and their applications in machine learning, computer vision, and hyperspectral imaging. Research Trends: Zhang’s recent work includes developing interpretable machine learning models (e.g., Tsetlin Machines), optimizing convolutional architectures for image processing, and applying automata theory to solve multi-armed bandit problems and channel selection in cognitive networks. His field spans theoretical analysis and practical implementations in AI, remote sensing, and health informatics. Scientific Contributions Co-developed advanced Tsetlin Machine variants for XOR/NOT operator convergence, disease forecasting, and image restoration Published in journals like IEEE Transactions on Pattern Analysis and Machine Intelligence , Information Sciences , and Applied Intelligence Explored Bayesian pursuit algorithms, hierarchical learning automata, and particle swarm optimization techniques Contact: xuan.zhang@uia.no

• Machine Learning
• Artificial Intelligence
• Data Science
• +۵ مورد دیگر

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's Pratt School of Engineering. Prior to joining Duke, he was a Postdoctoral Scholar Research Associate at the California Institute of Technology, and he earned his Ph.D. in Computer Science from UCLA. His research bridges theoretical foundations with practical applications in machine learning and artificial intelligence. Dr. Xu's research focuses on developing computationally- and data-efficient machine learning algorithms with strong theoretical guarantees, particularly in reinforcement learning, optimization, and high-dimensional statistics. His work addresses two fundamental challenges in sequential decision-making: efficient exploration with minimal interactions and robustness against distributional shifts. His research spans theoretical algorithm design, practical implementation, and real-world applications in bioinformatics and healthcare. His publication record demonstrates consistent high-impact contributions to top-tier conferences including ICML, NeurIPS, ICLR, AAAI, and AISTATS. The research trends show a progression from foundational work in non-convex optimization and multi-armed bandits toward increasingly sophisticated frameworks for robust reinforcement learning, with particular emphasis on distributional robustness, efficient exploration strategies, and practical applications. His work often bridges theoretical guarantees with empirical validation. NSF award on approximate sampling based exploration for sequential decision making Whitehead Scholar award from Duke University School of Medicine PIMCO Postdoctoral Fellowship in Data Science UCLA Outstanding Graduate Student Research Award Rising Stars in Data Science by University of Chicago Best Paper Award for Queer In AI: A Case Study in Community-Led Participatory AI at FAccT 2023 Featured Certification for Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits at TMLR Oral Presentation award at AAAI 2024 Dr. Xu actively mentors students and researchers, seeking highly motivated individuals with strong mathematical backgrounds for Ph.D. programs in Biostatistics & Bioinformatics, Computer Science, and Electrical & Computer Engineering at Duke. He has received multiple research grants including an NSF award on approximate sampling based exploration for sequential decision making. His service to the academic community includes roles as area chair for NeurIPS, ICML, ICLR, and AISTATS, as well as action editor for Transactions on Machine Learning Research. His research group develops algorithms that address fundamental challenges in sequential decision-making, with applications spanning healthcare, bioinformatics, and multi-agent systems. Current research directions include distributionally robust reinforcement learning, efficient exploration strategies, and applications of graph neural networks to biological problems.

Asaf Cohenمشاهده پروفایل

دانشیار

• Applied Probability
• Stochastic Processes
• Control Theory
• +۱۲ مورد دیگر

Asaf Cohen is an Associate Professor in the Department of Mathematics at the University of Michigan, Ann Arbor, affiliated with the College of Literature, Science, and the Arts. He holds a B.Sc., M.Sc., and Ph.D. from Tel-Aviv University (2005–2013). His research focuses on applied probability, stochastic processes, and control theory, with emphasis on mean-field games, mathematical finance, actuarial science, diffusion and large deviation analysis, machine learning, and risk-sensitive control. His work also addresses applications in stochastic networks, energy markets, epidemiology, and economics. Key research areas include diffusion approximations, large deviations, queueing theory, and partial differential equations. Dr. Cohen has contributed to the analysis of multiclass queueing systems, optimal dividend strategies, and strategic server behavior in heavy traffic regimes. His methods often involve advanced stochastic control techniques and game-theoretic models. He has published extensively on topics such as mean-field games, SIR models for epidemics, and Bayesian sequential testing. His academic contributions span theoretical advancements and practical applications in finance, insurance, and operations research.

Danielle Liمشاهده پروفایل

استاد

• Economics of innovation
• Labor economics
• Technology in the workplace
• +۴ مورد دیگر

Danielle Li is the David Sarnoff Professor of Management of Technology and a Professor at the MIT Sloan School of Management, specializing in the Technological Innovation, Entrepreneurship, and Strategic Management academic group. She is also a Faculty Research Fellow at the National Bureau of Economic Research (NBER). Her academic journey includes an AB in mathematics and the history of science from Harvard College and a PhD in economics from MIT. Prior to joining MIT, she taught at Harvard Business School and the Kellogg School of Management. AB in Mathematics and History of Science, Harvard College PhD in Economics, MIT Professor Li's research focuses on the economics of innovation and labor economics, with particular emphasis on how organizations evaluate ideas, projects, and people. She investigates the intersection of technology and workplace dynamics, especially how AI impacts worker productivity, the nature of work, and career trajectories in AI-intensive environments. Her work examines how businesses implement AI tools and the resulting effects on workforce composition and skill requirements. Her publication portfolio reveals a consistent focus on innovation economics, labor market dynamics, and the organizational implications of technology. Recent work increasingly centers on AI's workplace impact, with her 2025 Quarterly Journal of Economics paper 'Generative AI at Work' demonstrating how AI assistance increases worker productivity by 15% on average, with differential effects across experience levels. Her research combines rigorous economic analysis with practical business implications, spanning pharmaceutical innovation, hiring practices, promotion decisions, and gender gaps in the workplace. Best Paper Prize: 2017 FIRCG Conference Best Paper Prize: 2018 CEPR Management, Organizations, and Entrepreneurship Conference Best Paper Prize: 2017 Red Rock Conference Best Paper Prize: 2018 LBS Summer Finance Symposium Best Paper Prize: 2019 American Economic Journal: Applied Economics Professor Li's research has been supported by significant grants and has influenced both academic discourse and business practice. Her work on AI in the workplace has informed executive education programs at MIT Sloan, including 'Making AI Work: Machine Intelligence for Business and Society' and 'Artificial Intelligence' courses. She actively engages with media and business leaders to translate research findings into practical insights, frequently appearing in the New York Times, Wall Street Journal, and Economist. Her research on gender promotion gaps and hiring practices has particular relevance for organizational human resource policies. Professor Li is deeply embedded in MIT's AI research ecosystem, collaborating with colleagues across Sloan and CSAIL. She contributes to MIT's AI Expert Spotlight series, focusing on how businesses should implement AI responsibly and effectively. Her work bridges economic theory with practical business applications, particularly in understanding how AI transforms work processes and organizational structures.

Jonathan Scarlettمشاهده پروفایل

دانشیار

• Machine Learning
• Information Theory
• High-Dimensional Statistics
• +۳ مورد دیگر

Jonathan Scarlett is an Associate Professor jointly appointed in the Department of Computer Science, Department of Mathematics, and Institute of Data Science at the National University of Singapore (NUS). He also serves as Assistant Dean (Graduate Studies) in the School of Computing. His research focuses on information theory, machine learning, and high-dimensional statistics, with applications to optimization, group testing, and statistical inference. Education: Ph.D. (Information Engineering), University of Cambridge (2014) B.Eng. (Electrical Engineering) and B.Sci. (Computer Science), University of Melbourne (2010) Research Interests: Algorithmic foundations of machine learning and statistical estimation Information-theoretic limits and adaptive algorithms Applications in group testing, compressed sensing, and DNA storage Robust optimization under uncertainty and adversarial settings His work bridges theoretical guarantees with practical algorithm design, emphasizing scalable solutions for high-dimensional problems. Key Achievements: Recipient of Singapore NRF Fellowship (2018) and NUS Presidential Young Professorship Listed in MIT Technology Review's 'Innovators Under 35' Asia Pacific (2021) Over 100 publications in top venues like ICML, NeurIPS, and IEEE Transactions Advising & Grants: Supervised multiple PhD students in areas like Bayesian optimization, group testing, and compressed sensing Lead researcher on projects supported by NRF and NUS grants Developed novel frameworks for safe Bayesian optimization and robust bandit algorithms Labs & Collaborations: Active in the Information Theory and Statistical Learning Group at NUS, collaborating with global institutions like EPFL and MIT on data science challenges.

• Nonparametric Statistics
• High-Dimensional Statistics
• Inverse Problems
• +۳ مورد دیگر

Cristina Butucea is a Professor of Statistics and Machine Learning at ENSAE-CREST, Institut Polytechnique de Paris . She was nominated an IMS Fellow (2019) for her contributions to nonparametric and high-dimensional statistics. She has co-organized major conferences like Fréjus 2018 , Luminy 2019-2020 , and Oberwolfach 2021 , and serves as Associate Editor for ALEA . Fields of interest: Nonparametric statistics, quantum statistics, differential privacy, inverse problems, machine learning. Awards: IMS Fellowship, conference organization leadership. Research trends: Focuses on optimal estimation under privacy constraints, quantum state reconstruction, high-dimensional inference, and adaptive nonparametric methods. Email: Cristina.Butucea@ensea.fr | Cristina.Butucea@ip-paris.fr

Katharina Eggenspergerمشاهده پروفایل

پژوهشگر

• Automated Machine Learning (AutoML)
• Hyperparameter Optimization (HPO)
• Tabular Machine Learning
• +۱ مورد دیگر

Katharina Eggensperger is an Early Career Research Group Leader at the University of Tübingen , leading the AutoML for Science group within the Cluster of Excellence Machine Learning for Science . She previously completed her Ph.D. at the University of Freiburg under Frank Hutter and Marius Lindauer (2022), and actively contributes to the AutoML community through open-source tool development and competition leadership. Co-developer of AutoML.org tools Faculty member of IMPRS-IS Chair for multiple AutoML workshops/conferences (2019-2025) Her research focuses on automated machine learning (AutoML) with specific attention to: AutoML Systems Hyperparameter Optimization Tabular Machine Learning Scientific Applications of ML She has organized multiple AutoML schools and conferences, including serving as Program Chair for AutoML 2024 and Non-archival Track Chair for AutoML 2025. Her work emphasizes making machine learning accessible through automation while maintaining scientific rigor and interpretability, particularly for tabular data applications. Katharina actively recruits PhD students through IMPRS-IS and collaborates with institutions like the University of Freiburg and Cyber Valley .

Daniel Royمشاهده پروفایل

استاد

• Machine Learning
• Statistical Learning Theory
• Foundations of Statistics
• +۱۱ مورد دیگر

Daniel Roy is a Full Professor at the University of Toronto, holding cross-appointments in the Department of Statistical Sciences, Computer Science, Electrical and Computer Engineering, and the Department of Computer and Mathematical Sciences at UTSC. He is also a Canada CIFAR AI Chair and Research Director at the Vector Institute, reflecting his leadership in AI and machine learning research. His educational background includes a PhD, MEng, and BSc in Computer Science from MIT, where his doctoral work earned the MIT EECS Sprowls Award. Prior to joining Toronto, he was a Newton International Fellow at the Royal Society and a Research Fellow at Emmanuel College, University of Cambridge. His research centers on foundational principles in machine learning, statistics, and probabilistic reasoning. Key interests include statistical learning theory, Bayesian nonparametrics, probabilistic programming, and information-theoretic generalization. His work bridges theoretical computer science, mathematical logic, and applied probability. His recent publications, appearing in ICML, NeurIPS, COLT, and JMLR, reflect a strong focus on theoretical advances in generalization, online learning, and stochastic optimization. Themes include minimax rates, conditional mutual information, and the role of data in PAC-Bayes bounds. His group has made foundational contributions to probabilistic programming, including work on Church and the computability of conditional probability. NSERC Discovery Accelerator Supplement Ontario Early Researcher Award Google Faculty Research Award Newton International Fellowship MIT EECS Sprowls Award Daniel Roy advises numerous PhD students and postdoctoral researchers, many of whom have gone on to prestigious positions in academia and industry. His group actively collaborates with leading researchers in machine learning and statistics. He is also an Action Editor for the Journal of Machine Learning Research and Transactions of Machine Learning Research, underscoring his role in shaping the field. He leads a vibrant research group focused on theoretical machine learning and probabilistic modeling, and maintains active collaborations with institutions such as MIT, Cambridge, and the Vector Institute. He is also the founder and maintainer of the probabilistic-programming.org wiki, a key resource in the community.

• Sequential Decision Making
• Bandit Problems
• Theoretical Reinforcement Learning
• +۶ مورد دیگر

Claire Vernade is a Group Leader at the University of Tübingen in the Cluster of Excellence Machine Learning for Science. She leads an active research group focused on theoretical aspects of sequential decision making, with particular expertise in bandit problems and reinforcement learning theory. Her work bridges theoretical foundations with practical applications in scientific discovery. Her research interests span sequential decision making, bandit problems, theoretical Reinforcement Learning, Learning Theory, and principled learning algorithms. She has made significant contributions to understanding non-stationary environments, lifelong learning frameworks, and the theoretical foundations of bandit algorithms. Her work on "Eigengame: PCA as a Nash Equilibrium" received an Outstanding Paper Award at ICLR 2021. Dr. Vernade has been awarded prestigious grants including an Emmy Noether award (2022) for her FoLiReL project and an ERC Starting Grant (2024) for her ConSequentIAL project. Her current ERC project explores the role of Reinforcement Learning in developing Continual Learning agents, with applications to scientific domains like drug discovery and micro-chemistry. Emmy Noether award under the AI Initiative call (2022) ERC Starting Grant (2024) Outstanding Paper Award at ICLR 2021 She currently supervises three PhD students and actively recruits postdocs and PhD candidates through the IMPRS-IS and ELLIS doctoral programs. Her group collaborates extensively with the broader machine learning community, organizing workshops like FoRLaC at ICML 2024 and serving as co-chairs for tutorials at major conferences. Dr. Vernade is also deeply committed to diversity and inclusion in machine learning, co-leading initiatives like Women in Learning Theory and Tübingen Women in Machine Learning.

• Dynamic Decision Problems
• Equilibrium Models and Games
• Optimal Learning
• +۵ مورد دیگر

Prof. Sven Rady is a leading academic at the Department of Economics at the Hausdorff Center for Mathematics , University of Bonn. He serves as a Hausdorff Chair for Mathematical Economics and Deputy Spokesperson for Collaborative Research Centre TR224. Research Interests include dynamic decision problems, equilibrium models, optimal learning, and strategic experimentation, with significant contributions to information economics and stochastic game theory. His work bridges mathematical modeling with economic theory, focusing on markets, learning dynamics, and policy implications. Scientific Awards include Fellow of the Econometric Society (2023) Teaching Awards at the University of Bonn (2021, 2022) CESifo Outstanding Referee Award (2013) Teaching Award of the State of Bavaria (2005) Key Collaborations involve interdisciplinary research at the intersection of economics and mathematics. He leads projects in the CRC TR224 and contributes to HCM initiatives on probabilistic modeling and information economics.