Daniel M. Roy is a Professor at the University of Toronto with cross-appointments in the Departments of Computer Science and Electrical and Computer Engineering. He serves as Associate Chair, Statistics, and is a Research Director at the Vector Institute and a CIFAR Canada AI Chair. His research focuses on foundational principles of prediction, inference, and decision-making under uncertainty, spanning machine learning, statistics, mathematical logic, applied probability, and computer science. He has contributed to learning theory, statistical network analysis, probabilistic programming, and Bayesian nonparametric statistics. Education: Ph.D. in Computer Science from MIT (2011), advised by Leslie Kaelbling. Postdoctoral fellowships at the University of Cambridge (Newton International Fellow and Research Fellow). His research explores information theories of learning , online learning , and nonstandard foundations for decision theory . Recent work includes best paper awards at ICML 2024 and advancements in probabilistic programming systems like Church. His publications address problems in generalization bounds, causal bandits, neural network theory, and exchangeable random structures. Scientific Awards include the MIT/EECS George M. Sprowls Doctoral Dissertation Award and the ICML 2024 Best Paper Award. He advises students and postdocs across statistics, computer science, and machine learning, with alumni now holding positions at institutions like Princeton, Imperial College London, and the University of Chicago.
جستجوی استاد راهنمای دانشگاهی
برای مسیر پژوهشیتان، استاد راهنما، استاد دانشگاه و پژوهشگر مناسب را پیدا کنید و با آنها ارتباط بگیرید.
نمایش ۱۶-۳۰ از ۱۷۱ استاد راهنما
اطلاعات پروفایلها از صفحات عمومی دانشگاهها گرفته شده و ممکن است بهروز نباشد.
Dr. Kevin G. Jamieson is a faculty member at the University of Washington , School of Computer Science , with prior affiliations at the University of California, Berkeley (Department of Electrical Engineering and Computer Sciences) and the University of Wisconsin-Madison (Department of Electrical and Computer Engineering). His work spans machine learning, reinforcement learning, bandit algorithms, and robotics. Current university: University of Washington Academic rank: Professor His research focuses on: Bandit algorithms and sequential decision-making Optimization in non-stationary environments Reinforcement learning with real-world applications Multi-agent systems and game theory Efficient data selection for multimodal learning Human-in-the-loop AI systems Recent publications highlight his expertise in pure exploration strategies, robotic manipulation, and bridging simulation-to-reality gaps in RL. He has mentored numerous collaborators, though formal student advising details are not explicitly listed here. No scientific awards are mentioned in the provided data.
Hamed Rahimianمشاهده پروفایل
استادیار
Dr. Hamed Rahimian is an Assistant Professor in the Department of Industrial Engineering at Clemson University. He holds a Ph.D. in Industrial and Systems Engineering from The Ohio State University (2018), an M.Sc. from The University of Arizona (2012), and B.Sc./M.Sc. degrees from Sharif University of Technology (2008/2011). Prior to Clemson, he was a Postdoctoral Research Fellow at Northwestern University under Prof. Sanjay Mehrotra. His research focuses on data-driven decision-making under uncertainty, including stochastic optimization, distributionally robust optimization, and risk-averse methodologies. He has published in top journals such as Mathematical Programming , SIAM Journal on Optimization , and Operations Research . Education: Ph.D. Industrial and Systems Engineering, The Ohio State University (2018) M.Sc. Industrial Engineering, The University of Arizona (2012) B.Sc./M.Sc. Industrial Engineering, Sharif University of Technology (2008/2011) His research has been recognized with awards including the Harold W. Kuhn Award (2022), Runner-Up INFORMS Computing Society Student Paper Award (2017), and 2nd Place IISE Pristker Dissertation Award (2019). He serves as an Associate Editor for INFORMS Journal on Computing and Sharif Journal of Industrial Engineering & Management . Grants & Advising: He secured an Air Force grant (2024) on multistage stochastic programming. His research group focuses on advancing optimization under uncertainty with applications in healthcare, energy, and supply chains. Labs/Teams: Leads a research group in Clemson’s Industrial Engineering department, collaborating on projects in distributionally robust optimization and data-driven decision-making.
Moïse Blanchardمشاهده پروفایل
استادیار
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. 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.
Claire Vernadeمشاهده پروفایل
پژوهشگر
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.
Xuan Zhangمشاهده پروفایل
دانشیار
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
Pan Xuمشاهده پروفایل
استادیار
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
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.
- 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 .
Claire Vernadeمشاهده پروفایل
استادیار
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.
- AI-enabled communications
- Green and energy-efficient communications
- Online optimization and machine learning
- +۶ مورد دیگر
E. Veronica Belmega is a Full Professor at ESIEE Paris (Université Gustave Eiffel) and a researcher at the LIGM laboratory in Marne-la-Vallée, France. Previously, she served as an Associate Professor at ENSEA graduate school and Deputy Director of the ETIS laboratory in Cergy. She holds an Engineer Degree from the University Politehnica of Bucharest, M.Sc. and Ph.D. from Université Paris-Sud 11, and an HDR habilitation from Université de Cergy-Pontoise. Her research focuses on AI-driven communication systems, energy efficiency, online optimization, and cyber-physical security, with a strong emphasis on applications in smart grids and IoT. Her work spans securing wireless communications against adversarial attacks, optimizing resource allocation in cognitive radio networks, and leveraging machine learning for GNSS localization and MIMO systems. Notable contributions include game-theoretic frameworks for PMU deployment and energy-efficient NOMA systems. Belmega has received prestigious awards such as the 2021 CY Alliance Award and the L’Oréal-UNESCO fellowship, and serves as an Area Editor for IEEE Trans. on Machine Learning in Communications and Networking. Current projects include a CEA LETI postdoc position on AI localization and a PEPR 5G project. She actively contributes to special issues like the EURASIP JASP on sustainable wireless communications. Belmega’s advising includes PhD student S. Maleki, co-author of her 2024 IEEE SmartGridComm Best Paper Award-winning work.
Yikun Banمشاهده پروفایل
دانشیار
- Reinforcement Learning
- Data Mining
- Neural Networks
- +۷ مورد دیگر
Yikun Ban is a tenure-track Associate Professor in the School of Computer Science and Engineering at Beihang University, where he is a member of the State Key Laboratory of Software Development Environment. He earned his PhD in Computer Science from the University of Illinois Urbana-Champaign (2023), MS in Computer Science from Peking University (2019), and BS in Software Engineering from Wuhan University (2016). PhD: University of Illinois Urbana-Champaign (2023) MS: Peking University (2019) BS: Wuhan University (2016) His research focuses on principled algorithms for reinforcement learning with human feedback, neural contextual bandits, and exploration-exploitation problems. He develops frameworks combining deep learning with bandit theory for applications in recommendation systems, disinformation detection, and dynamic graph learning. Recent publications address: Robust neural contextual bandits (NeurIPS 2024) Graph neural bandits (KDD 2023) Meta-learning for bandit scheduling (NeurIPS 2023) Clustering in contextual bandits (WWW 2021, AAAI 2021) Honors include the NeurIPS Scholar Award and recognition as ICML Outstanding Reviewer . His open-source LOCB repository provides Python implementations for contextual multi-armed bandit algorithms with local clustering, supporting applications in recommendation systems and online learning.
Haipeng Luoمشاهده پروفایل
دانشیار
Haipeng Luo is an Associate Professor at the Thomas Lord Department of Computer Science, University of Southern California, holding the IBM Early Career Chair. He previously worked as a Postdoctoral Researcher at Microsoft Research, NYC, and has held visiting roles at Google and Amazon. His research focuses on developing practical machine learning algorithms with strong theoretical guarantees, particularly in online learning, bandit problems, reinforcement learning, and game theory. PhD in Computer Science, Princeton University (2011–2016) BSc in Computer Science, Peking University (2007–2011) His work spans adversarial and stochastic environments, addressing challenges in reinforcement learning, game dynamics, calibration, and omniprediction. Recent publications highlight advancements in regret minimization, game equilibrium computation, and robust optimization frameworks. Key contributions include algorithms for zero-sum games, bandit problems with feedback graphs, and theoretical analyses of convergence properties in multi-agent systems. Scientific accolades include Best Paper Awards at COLT 2021, COLT 2018, NeurIPS 2015, and ICML 2015. He has received prestigious grants such as the NSF CAREER Award (2020), Google Faculty Research Award (2020), and NSF CRII Award (2018). His students have secured academic and industry positions, and he actively teaches graduate courses in machine learning and online optimization.
Sadegh Talebiمشاهده پروفایل
استادیار
Sadegh Talebi is a Tenure Track Assistant Professor in the Machine Learning Section at the Department of Computer Science, University of Copenhagen . His research focuses on theoretical aspects of reinforcement learning, Markov decision processes, online learning, stochastic multi-armed bandit problems, and resource allocation in networks. Education BSc in Electrical Engineering (minor: Electronics) from Iran University of Science and Technology (IUST) (2004) MSc in Electrical Engineering (minor: Communication Systems) from Sharif University of Technology (2006) PhD in Electrical Engineering from the Department of Automatic Control at KTH Royal Institute of Technology (supervised by Alexandre Proutiere and Mikael Johansson) Research Specializes in theoretical foundations of reinforcement learning and online learning Key contributions in stochastic optimization, MDPs, and bandit algorithms Collaborates on applications in resource allocation and quantum computing Publications include high-impact work on offline RL, differentially private exploration, and scalable MDP solutions in journals like Neural Processing Letters and conferences such as NeurIPS and UAI.