Find Academic Supervisors

Yishay MansourView profile

Professor

• Machine Learning
• Reinforcement Learning
• Algorithmic Game Theory
• +4 more

Yishay Mansour is a Professor of Computer Science at Tel Aviv University's School of Computer Science, where he has been a faculty member since 1992. He previously served as the first head of the Blavatnik School of Computer Science (2000-2002) and currently directs the Israeli Center of Research Excellence in Algorithms. He maintains a part-time research position at Google Research in Tel Aviv and has held previous positions at Microsoft Research in Israel. Professor Mansour received his PhD from MIT in 1990, followed by a postdoctoral fellowship at Harvard and a position as Research Staff Member at IBM T.J. Watson Research Center. His research spans several key areas including machine learning (particularly reinforcement learning and multi-armed bandits), algorithmic game theory, communication networks, and theoretical computer science. He has published over 100 journal papers and 200 conference proceedings, with recent work focusing on regret minimization, differential privacy, and reinforcement learning theory. His recent publications demonstrate a strong focus on theoretical foundations of machine learning, with particular emphasis on bandit algorithms, reinforcement learning, and game theory. The trends in his work show increasing integration of societal challenges like fairness and privacy into learning algorithms, alongside continued theoretical advances in optimization and learning guarantees. ACM Fellow (2014) ELLIS Fellow (2020) Asia-Pacific Artificial Intelligence Association Fellow (2022) AI Industry Alliance Fellow (2023) ERC Advanced Grant (2020) Multiple best paper awards including at COLT (2007), EC (2007), and EC (2025) Professor Mansour has supervised over a dozen doctoral students and numerous master's students, with his advisees working on topics ranging from reinforcement learning algorithms to algorithmic game theory and online learning. He has served on numerous program committees including as Program Chair for STOC (2016) and COLT (1998), and is currently an associate editor for several distinguished journals. His research has been supported by multiple grants from the Israel Science Foundation, ERC Advanced Grant, and other funding bodies. He leads the COLT-MDP lab which focuses on advancing the theory of reinforcement learning through three pillars: compact representation, efficient computation, and addressing societal challenges including fairness and privacy in learning algorithms.

Alberto José Bugarín DizView profile

Professor

• Machine Learning
• Natural Language Generation
• Soft Computing
• +5 more

Alberto José Bugarín Diz is a Full Professor of Artificial Intelligence at the University of Santiago de Compostela (USC), where he serves as coordinator of the Intelligent Systems Group (GSI), founded in 1990 and recognized as a competitive reference group by the Xunta de Galicia since 2006. He previously served as Deputy Director of the School of Engineering of the University of Santiago de Compostela (ETSE) and currently acts as the USC coordinator of the Degree in Artificial Intelligence taught across the three universities in Galicia. His research focuses on various areas of artificial intelligence and its applications, including natural language generation (Data-To-Text systems), soft computing, automatic learning, and approximate knowledge and reasoning representation. He has co-authored nearly 230 scientific papers and participated in over 63 R&D projects and innovation contracts, serving as principal researcher in 25 of them. His work spans healthcare applications, manufacturing processes, conversational agents, and linguistic descriptions of data, with particular emphasis on making AI systems more transparent and understandable to users. Prof. Bugarín Diz is actively involved in the AI community, currently serving as a Board Member of the Spanish Society for Artificial Intelligence (AEPIA), Secretary of the Spanish Society for Natural Language Processing (SEPLN), and as a member of the Organizing Committee of the 27th European Conference on Artificial Intelligence (ECAI), which took place in Santiago de Compostela in October 2024. He also participates in the TELSEC4TAI network about 'Trustworthy AI: technical, ethical, legal, cultural and socio-economic challenges.' His recent publications reveal a strong focus on explainable AI, trustworthy systems, and the application of fuzzy logic to complex reasoning problems, particularly in medical diagnosis, automotive manufacturing, and conversational systems. His work consistently bridges theoretical AI concepts with practical applications that address real-world challenges in healthcare, industry, and human-computer interaction. Board Member, Spanish Society for Artificial Intelligence (AEPIA) Secretary, Spanish Society for Natural Language Processing (SEPLN) Organizing Committee Member, 27th European Conference on Artificial Intelligence (ECAI 2024) Coordinator, Intelligent Systems Group (GSI) USC Coordinator, Degree in Artificial Intelligence (Galicia)

• Mathematical Foundations of Machine Learning
• Explainable Artificial Intelligence
• Online Convex Optimization
• +4 more

Tim van Erven is an Associate Professor of Machine Learning at the Korteweg-de Vries Institute for Mathematics within the Faculty of Science at the University of Amsterdam. His research focuses on the mathematical foundations of machine learning, with particular expertise in online convex optimization, statistical learning theory, and explainable AI. He leads a research group dedicated to developing mathematically rigorous machine learning methods that work effectively without manual fine-tuning. His research interests span the mathematical foundations of machine learning, with emphasis on explainable machine learning, adaptive methods in online convex optimization, faster-than-minimax rates for 'easy data' in statistical learning, PAC-Bayesian concentration inequalities, and statistical learning theory with frequentist analysis of Bayesian methods. His work bridges theoretical guarantees with practical applications, recently shifting toward formal mathematical analysis of explainability methods for black-box AI systems. His recent publications reveal a clear evolution from foundational work in online learning and statistical theory toward explainable AI, with increasing focus on theoretical guarantees for concept learning and algorithmic recourse. The publications demonstrate strong methodological rigor while addressing practical challenges in interpretability and robustness of machine learning systems. Scientific Awards: VICI grant by the Dutch Research Council (2025) VIDI grant by the Dutch Research Council (2019) TOP grant by the Dutch Research Council (2016) NIPS 2014 outstanding reviewer award Rubicon grant by the Dutch Research Council (2011) Van Erven serves in significant academic leadership roles including as a member of the board of directors for COLT, co-chair for the AI & Mathematics initiative, and organizer of the thematic seminar on machine learning. He has successfully secured multiple competitive research grants and leads a research group working on the Mathematical Foundations for Explainable AI project, with several PhD and Postdoc positions currently open.

Noam KoenigsteinView profile

Professor

• Recommender Systems
• Machine Learning
• Collaborative Filtering
• +5 more

Prof. Noam Koenigstein is a Professor in the Department of Industrial Engineering at Tel Aviv University's Iby and Aladar Fleischman Faculty of Engineering. His research focuses on developing scalable machine learning solutions for real-world recommendation systems, with extensive industry collaborations including Microsoft (Xbox) and Yahoo! Music. His primary research interests include recommender systems, collaborative filtering, and neural approaches to user modeling. He pioneered neural item embedding techniques like Item2Vec and advanced Bayesian methods for diversity-aware recommendations using Determinantal Point Processes. His work consistently bridges theoretical machine learning with industrial-scale deployment challenges. Analysis of his publication record reveals a strong evolution from traditional matrix factorization toward deep learning and attention-based architectures, always emphasizing practical scalability and addressing cold-start problems. His research demonstrates exceptional continuity in solving core recommendation challenges across domains including e-commerce, music, and video services. Scientific recognition includes: Best paper runner up award at TVX 2014 for group viewing pattern analysis Prof. Koenigstein has led multiple industry-academia partnerships that produced deployable recommendation frameworks, notably for Xbox Movies and Windows Store. His invited RecSys 2017 talk highlighted critical gaps between academic research and industrial requirements in recommender systems, establishing him as a leading voice in practical recommendation science.

Shu XieView profile

Researcher

• Island Biogeography
• Evolutionary Ecology
• Phylogenetics
• +5 more

Shu Xie is a Guest Researcher at the Faculty of Science and Engineering , University of Groningen, affiliated with the Etienne group specializing in Theoretical and Evolutionary Community Ecology. Their ongoing PhD project (2018–present) at Naturalis Biodiversity Center (Netherlands) focuses on "The effect of traits on insular diversification" , co-supervised by L. Valente. Shu Xie's research lies at the intersection of Island Biogeography Phylogenetics Speciation Modeling Approximate Bayesian Computation (ABC) DAISIE Framework Development contributing to UN Sustainable Development Goals related to biodiversity conservation. Recent work emphasizes Computational methods for trait-dependent diversification ABC parameter inference in island phylogenetic models DAISIE software for R Evaluating colonization-extinction dynamics Identifying summary statistics for Bayesian model validation with publications in journals like Evolution and Geoderma .

• Artificial Intelligence
• Machine Learning
• Game Theory
• +7 more

Frans A. Oliehoek is a Full Professor in Interactive Learning and Decision Making at the Department of Intelligent Systems, Delft University of Technology. He co-leads the Sequential Decision Making group and serves as director and co-founder of the ELLIS Delft Unit. His academic affiliations include senior membership at AAAI, board membership at IFAAMAS, and associate editor roles for JAIR and AIJ. His research focuses on interactive learning and decision making , integrating AI, machine learning, and game theory to develop algorithms for agents interacting in complex, dynamic environments. Key themes include Bayesian reinforcement learning , influence-based abstraction , multi-agent coordination , and uncertainty modeling in real-world applications like traffic control, human-AI collaboration, and e-commerce agents. Recent publications highlight advancements in Bayesian RL with factored POMDPs , multi-agent safety guarantees , and state abstraction . His work spans theoretical foundations (e.g., Nash equilibria, MDP homomorphic networks) and practical frameworks (e.g., SHARPIE for human-AI experiments). Scientific contributions include: ELLIS Fellowship Senior AAAI Membership Best Paper Award at ALA 2021 Outstanding Paper Award at RLC 2024 He has advised students like Miguel Suau and Robert Loftin, with applications in multi-agent reinforcement learning , Bayesian planning , and human-AI interaction . Collaborations span institutions like UC Berkeley, University of Amsterdam, and MIT.

• Health Economics
• Decision Modelling
• Mathematical Modelling
• +6 more

Professor Alan Brennan is Professor of Health Economics and Decision Modelling at the School of Medicine and Population Health, University of Sheffield, England. He leads a large team of approximately 35 academic staff at ScHARR (School of Health and Related Research) focused on methodological and applied research using mathematical modeling in health and healthcare. With over 25 years of experience, he has developed and applied modeling approaches to support healthcare decision-making nationally and internationally across various diseases, interventions, and policy issues. His educational background includes a BSc in Mathematics from Imperial College London and an MSc in Operational Research from the London School of Economics, followed by PhD studies at Sheffield. Before joining the University, he worked in and led the Trent Operational Research Unit within the NHS. Professor Brennan's research interests center on mathematical modeling approaches to inform decision-making in health and healthcare, with significant contributions in alcohol policy (particularly minimum unit pricing), public health economics, and health technology assessment. He has collaborated extensively with organizations including NICE, NIH, MRC, ESRC, and the EU. His work has influenced government policy on minimum unit pricing for alcohol in multiple countries including the UK, Scotland, Canada, Wales, the EU Commission, and Republic of Ireland. His publication record shows a consistent focus on health economic modeling, with recent work expanding into areas including dietary policy mechanisms, breast cancer bone health management, dataset interoperability, diabetic foot ulcer risk factors, and cost-effectiveness of screening programs. The research demonstrates a progression toward more sophisticated modeling techniques including agent-based simulation, Bayesian networks, and value of information analysis. Regular expert on NICE Scientific Advice Programme panels Principal investigator or co-investigator on over 19 research programs and projects Contributor to Wellcome Doctoral Training Centre in Public Health Economics and Decision Science Developer of MSc Health Economics and Decision Modelling courses Professor Brennan has established the Sheffield Alcohol Research Group with Professor Meier, becoming a leading international center for alcohol policy and epidemiological modeling research. His team has built a substantial portfolio of work around screening and prevention of diabetes, smoking and alcohol behaviors, and physical activity promotion, all grounded in novel mathematical modeling approaches to support health decision-making.

Aislinn KeoghView profile

Researcher

• Cognitive Science
• Linguistics
• Language Evolution
• +3 more

Aislinn Keogh is a Postdoctoral Research Associate at the Department of Psychology, Durham University, employed under the ERC Starting Grant project Children as Agents of Cultural Evolution led by Dr. Sheina Lew-Levy. Her work integrates computational modeling, observational research, and experimental methods to study social learning and language dynamics in children and adults. Education: Bachelor's in Linguistics, Newcastle University (2013) MSc in Evolution of Language and Cognition, University of Edinburgh (2021) PhD in Linguistics, University of Edinburgh (2025) Her research focuses on how cognitive and motor constraints in language production influence learning, communication, and long-term linguistic evolution. Current projects examine phonetic clustering trade-offs, working memory effects on regularization, task impacts on morphological rule acquisition, and redundancy's role in mitigating individual learning differences. Recent work involves collaborations with Elizabeth Pankratz and Professor Gary Lupyan, leveraging agent-based models and Approximate Bayesian Computation. Publications span Cognitive Science , Evolang Conference Proceedings , and preprint platforms like PsyArXiv.

Pedro Pintado Jorge GonçalvesView profile

Senior Lecturer

• Computational neuroscience
• Machine Learning
• Simulation-based inference
• +4 more

Pedro Pintado Jorge Gonçalves is a Senior Lecturer at the Faculty of Engineering Sciences at KU Leuven, with primary affiliation in the Department of Electrical Engineering and strong ties to the Department of Computer Science. He leads the Gonçalves lab at the VIB-KU Leuven Center for Neuro Electronics Research Flanders (NERF), and is also a member of the KU Leuven Brain Institute and Leuven.AI Institute for Artificial Intelligence. His educational background includes training as a physicist with a focus on neuroscience applications. His research integrates machine learning with computational neuroscience to develop methods for extracting mechanistic insights from complex neural data. His work specializes in simulation-based inference techniques that bridge data-driven and theory-driven approaches in neuroscience. The publication trends reveal a strong focus on developing and applying machine learning methods to neuroscience problems, with particular emphasis on neural circuit modeling, biophysical simulations, and the development of computational tools like the sbi toolkit. His research spans multiple scales from single neurons to population dynamics and behavior. As an educator, he teaches courses including Calculus and Mathematical Engineering, and mentors numerous students through his lab. His collaborative approach is evident in his extensive co-authorship network across computational neuroscience and machine learning fields. Dr. Gonçalves actively supervises multiple PhD and master's students in his lab, fostering the next generation of computational neuroscientists. His research is supported by multiple ongoing projects including 'Simulation-based inference for mechanistic models of neural dynamics' (2025-2029) and 'Computational research into the principles of robustness in neural systems' (2023-2027). His laboratory focuses on combining theoretical models with advanced machine learning methods to design more accurate neural models, quantitatively test mechanistic hypotheses, and derive experimentally-testable predictions about neural systems in health and disease.

Ivashko Viktor ViktorovychView profile

Assistant Professor

• Computational Physics
• Solid State Physics
• Statistical Mechanics
• +3 more

Ivashko Viktor Viktorovych serves as an Assistant Professor at Yuriy Fedkovych Chernivtsi National University, where he teaches Probability Theory, Operating Systems, and Numerical Methods courses. Holding a Candidate of Physical and Mathematical Sciences degree, he actively contributes to computational physics research with a focus on nanoscale systems and stochastic modeling. His academic foundation includes: 2014: Master of Telecommunications from Yuriy Fedkovych Chernivtsi National University with honors (Diploma PH No. 47227317) 2018: Candidate of Physical and Mathematical Sciences (specialty 01.04.07 – Solid State Physics) for dissertation 'Features of Transition Phenomena between Low- and High-Spin States of Spin-Crossover Compounds' (DK No. 046497) Dr. Ivashko's research centers on computational modeling of physical systems using Monte Carlo methods, particularly investigating spin-crossover compounds and nanomaterials. His work bridges solid-state physics and statistical mechanics, with significant applications in molecular electronics and nanodevice development. Recent publications reveal consistent focus on impurity effects in nanoparticles, magnetic properties of carbon-based systems, and pressure-induced electronic bistability in coordination polymers, demonstrating methodological expertise in simulating nanoscale phase transitions. His scientific recognition includes: Gratitude for significant scientific achievements (2016-2017) Through scientific consulting for MPP 'PROM.SOFT' and authorship of 12+ textbooks/monographs, he actively shapes academic curricula. Professional development includes Sigma Software's Teachers’ Smart Up programs (2023-2024), Softserve's Tech Summer Bootcamp, and Coursera specializations in Python and web development. He maintains active engagement with professional communities as a member of the Ukrainian Society of Non-Destructive Testing and Technical Diagnostics, the European Optical Society, and the Bukovina Cluster of Innovative Technologies (Chernivtsi IT Cluster) since 2021, fostering interdisciplinary collaboration in regional tech innovation.

Glenn HaweView profile

Lecturer

• Machine Learning
• Multi-objective Optimization
• Bayesian Optimization
• +4 more

Dr. Glenn Hawe is a Lecturer at Ulster University's School of Computing within the Faculty of Computing, Engineering and the Built Environment. He has been with the university since 2013 and is a member of the Artificial Intelligence Research Group. His work focuses on the intersection of machine learning, optimization, and emergency response systems. Education: MPhys in Mathematics and Physics (first class) from University of Warwick (2004) PhD in Electronics and Electrical Engineering from University of Southampton (2008) Dr. Hawe's research spans machine learning, multi-objective optimization, and agent-based simulation, with applications in emergency response systems, robotics, and autonomic computing. His work often explores how computational methods can address complex real-world problems, particularly in the context of resource allocation during major incidents. He has developed innovative approaches in Bayesian optimization and has made significant contributions to the field of autonomic pulse communications for robot swarms. Analysis of his recent publications shows a clear trajectory toward increasingly sophisticated applications of machine learning in robotics and emergency response systems. His work demonstrates growing integration of autonomic computing principles with swarm robotics, particularly for space applications and disaster response scenarios. The research shows increasing focus on explainability in AI systems alongside practical implementation in constrained environments. Scientific Recognition: Won two best paper awards at conferences during his PhD Work featured in 2009 'From recession to recovery' report by Universities UK as an example of successful academia-industry collaboration Dr. Hawe has been actively involved in multiple Knowledge Transfer Partnership (KTP) projects with industry partners and has served as a reviewer for prestigious journals including Journal of Simulation, International Journal of Machine Learning and Cybernetics, and IEEE Transactions on Magnetics. He is a member of the EPSRC peer review college and serves on the technical committee for the Science and Information Conference. His current projects include decarbonization of maritime transportation and autonomy for CubeSats. As part of the Artificial Intelligence Research Group, Dr. Hawe collaborates on projects involving agent-based simulation for emergency response and autonomic computing applications. His work on the REScUE project at Durham University laid the foundation for his current research in computational approaches to major incident management.

• Quantum Computing
• Machine Learning
• Algorithms
• +4 more

Chunhao Wang is an Assistant Professor in the Department of Computer Science and Engineering at an unspecified university. His research focuses on quantum algorithms, optimal control of quantum systems, and their applications in computational chemistry and machine learning. He has active NSF-funded projects on quantum control and continuous-time open quantum systems. Active NSF Grants: FET Small (2023-2026), CAREER (2023-2028) His work spans quantum computing, algorithm design, and solving high-dimensional problems in optimization and statistical mechanics. Recent publications highlight quantum speedups for classical algorithms and efficient simulation of non-Markovian systems. Collaborations include researchers like Li, X. and Wu, X.

Sutanu GayenView profile

Assistant Professor

• Theory of Machine Learning
• Algorithms
• Bayesian Networks
• +3 more

Sutanu Gayen is an Assistant Professor in the Department of Computer Science and Engineering at the Indian Institute of Technology Kanpur. His research focuses on theoretical aspects of machine learning, algorithms, and computational statistics. Designing algorithms for Bayesian networks and causality Complexity analysis of distribution learning Applications in high-dimensional statistical modeling His recent publications explore challenges in total variation distance computation, Gaussian tree models, and interventional distribution learning. Courses taught include advanced algorithms for machine learning and data structures. Research connects fundamental computational limits with practical statistical learning tasks.

• Statistical Science
• Data Science
• Machine Learning
• +7 more

Nick Whiteley is a Professor in the School of Mathematics at the University of Bristol and serves as Director of the Institute for Statistical Science. He also held a Heilbronn Chair in Data Science and previously directed the EPSRC Centre for Doctoral Training in Computational Statistics and Data Science. His research spans statistical science and data science with interdisciplinary applications. Education : Ph.D. (University of Cambridge, 2009), M.Eng. (University of Oxford, 2003) Whiteley's research focuses on sequential Monte Carlo methods , Bayesian inference , hidden Markov models , and nonlinear filtering . His work connects statistical theory with practical applications in epidemic modeling, graph representation, and temporal data analysis. His recent publications emphasize scalable algorithms for high-dimensional problems and theoretical foundations of approximation methods. Key article trends include epidemic modeling , dynamic network analysis , stochastic processes , and machine learning theory . Sub-fields span from computational statistics to geometric methods in AI. Whiteley has received prestigious recognition through the Heilbronn Chair and Brunel Research Fellowship.

Seth FlaxmanView profile

Associate Professor

• Machine Learning
• Bayesian Statistics
• Spatiotemporal Statistics
• +5 more

Seth Flaxman is an Associate Professor of Computer Science at the University of Oxford and a Tutorial Fellow at Jesus College. His research focuses on scalable Bayesian machine learning and spatiotemporal statistics, with applications in public policy, global health, and social science, particularly in areas like public health, orphanhood, and computational epidemiology. BA in Mathematics and Computer Science, Harvard University (2004-2008) PhD in Machine Learning and Public Policy, Carnegie Mellon University (2011-2015) His work bridges computational statistics and machine learning with real-world challenges, including disease modeling for COVID-19, analysis of social media filter bubbles, and statistical methods for big data paradoxes. He actively supervises DPhil, Master’s, and undergraduate research projects. Key trends in his recent publications include applications of Gaussian processes and Bayesian hierarchical models to global health challenges such as HIV risk mapping, SARS-CoV-2 surveillance, and spatiotemporal forecasting. His research integrates multimodal data (e.g., satellite imagery, census microdata) and emphasizes scalable inference algorithms. Scientific Awards : Samsung AI Researcher of the Year Award (2020) Best Student Paper Award, KDD 2015 Suresh Konda Award for Heinz first paper His EPSCRC Fellowship Award (£1.18 million) supports research on Spatiotemporal Statistical Machine Learning. He collaborates with institutions including Imperial College London, University of Copenhagen, and the World Health Organization.