Find Academic Supervisors

Ralf KellnerView profile

Professor

• Economics
• Data Science
• Statistics
• +2 more

Professor Ralf Kellner holds the Chair of Financial Data Analytics at the University of Passau, Faculty of Economics. His work integrates economics, data science, and statistics, focusing on empirical and application-oriented research to explore how statistical learning and AI can uncover insights in data-driven decision-making processes that generate economic value. He also teaches courses such as Deep Learning and Text Analysis in Finance, Financial Data Analytics and Machine Learning, and Scientific Computing with Python. His research examines the intersection of financial markets, statistical learning, and artificial intelligence, with specific interests in modeling adverse financial developments, systemic risks, and analyzing text data via domain-specific language models. Publications highlight collaborations with researchers like D. Rösch and N. Gatzert. Recent publications include work on hybrid service agents, quantile neural networks, default resolution time analysis, Bayesian sovereign bond risk models, and international diversification studies. His methodological approaches span extreme value theory, quantile regression, and multivariate statistical techniques applied to financial and insurance contexts. Contact: ralf.kellner@uni-passau.de

• Bayesian Statistics
• Statistical Modeling
• Hypothesis Testing
• +2 more

Scott Goddard serves as Assistant Professor of Statistics at the University of Alaska Fairbanks since 2015, holding a PhD from Texas A&M University (2015). His office is located in CH 201E with contact via sdgoddard@alaska.edu. His research spans Bayesian Statistics , focusing on theoretical development and practical applications. Key interests include hypothesis testing , variable selection , and Bayesian philosophy , with methodologies applied to engineering, ecological, and petroleum systems. Recent work demonstrates interdisciplinary collaboration through reservoir characterization algorithms and wildlife movement modeling. Publications reveal a trend toward real-world Bayesian implementations, particularly in energy extraction and ecological monitoring, often co-authored with graduate researchers. His advising includes UAF students Yuhun and J. M. Eisaguirre, whose thesis work contributed to peer-reviewed publications in SPE Reservoir Evaluation & Engineering and Methods in Ecology and Evolution.

Hideyuki SuzukiView profile

Professor

• Nonlinear Dynamics
• Hybrid Systems
• Many-Body Dynamics
• +5 more

Hideyuki Suzuki is a Professor at the Department of Information and Physical Sciences , Graduate School of Information Science and Technology , Osaka University , where he has been employed since April 2016. His research spans nonlinear dynamics , hybrid systems , and many-body dynamics , with applications to power systems , brain modeling , and epidemic networks . 2001 : Ph.D. in Mathematical Engineering and Information Physics, University of Tokyo 1998 : M.Eng. in Mathematical Engineering and Information Physics, University of Tokyo 1996 : B.Sc. in Mathematics, University of Tokyo His research interests focus on nonlinear dynamical systems , particularly those with discontinuities or large-scale interactions , such as chaotic billiards , hybrid systems , and spatio-temporal chaos . He explores computational applications in machine learning (e.g., chaotic Boltzmann machines ), epidemiology (e.g., vaccine allocation models ), and power grid stability . The 15 most recent articles highlight his work in photonic computing , nonlinear sampling algorithms , and chaotic dynamics in engineering and biology . Key trends include interdisciplinary applications of nonlinear mathematics to renewable energy , neuroscience , and epidemic spread . Scientific awards include: 2022 Osaka University Prize 2018 JSIAM Best Paper Award for Hamiltonian Monte Carlo (2017) He leads the Nonlinear Mathematics Course laboratory, which accepts graduate and undergraduate students. His team investigates hybrid dynamical systems , chaotic computation , and real-world modeling in fields like traffic dynamics and epidemic networks . Research is supported by grants from JST CREST and ALCA-Next programs.

Marcel KolloviehView profile

Researcher

• Generative models
• Graphs
• Time series
• +4 more

Marcel Kollovieh is a researcher at the Technical University of Munich (TUM), affiliated with the TUM School of Computation, Information and Technology and the Department of Computer Science . He is part of the Data Analytics and Machine Learning (DAML) Lab under the mentorship of Prof. Dr. Stephan Günnemann. Education B.Sc. and M.Sc. in Informatics from TUM Research Interests : Marcel focuses on generative models (including variational autoencoders, diffusion models, and score-based models), graphs , and time series , with additional work on hierarchical structures , robustness , and Bayesian learning . His publications span conferences like ICML , ICLR , and NeurIPS , alongside journals such as TMLR . Themes include token merging , flow matching , and adversarial robustness in temporal data, alongside probabilistic clustering and diffusion models . Lab and Team : Marcel works within the DAML Lab at TUM.

Gal ElidanView profile

Associate Professor

• Probabilistic Graphical Models
• Machine Learning
• Copula Models
• +3 more

Gal Elidan is an associate professor in the Department of Statistics at the Hebrew University of Jerusalem, Faculty of Social Sciences. His work bridges statistical theory with practical applications in machine learning and artificial intelligence. Dr. Elidan's research focuses on Probabilistic Graphical Models , with emphasis on fundamental representations and methods for inference and learning in large-scale domains. His work addresses structure learning, discovery of hidden variables, transfer of knowledge between related tasks, and nonlinear high-dimensional representations of continuous or hybrid distributions. He also applies these techniques to real-life applications including computational biology, machine vision, and medical informatics, with recent focus on principled techniques for medical diagnosis. His publication record shows consistent contributions to top machine learning venues with a recent emphasis on copula models for high-dimensional data. His work demonstrates a progression from foundational graphical model research to specialized applications in medical informatics and time series analysis. Scientific recognition includes: Runner-up for Best Student Paper Award at UAI 2004 Best Paper Award at ISMB 2001 Dr. Elidan serves on the editorial board of the Journal of Artificial Intelligence Research (JAIR) and has contributed to the development of important software tools including FastInf, a library for large-scale inference of graphical models, and LibB, a package for Bayesian network inference and learning. He has organized significant academic events including the NIPS 2011 Workshop on Copulas in Machine Learning and co-organized the PASCAL2 Probabilistic Inference Challenge and UAI 2010 Approximate Inference Challenge.

Debabrota BasuView profile

Assistant Professor

• Machine Learning
• Reinforcement Learning
• Bandit Algorithms
• +6 more

Debabrota Basu is a tenured faculty member (Inria Starting Faculty Position - ISFP) at the Scool team (previously called SequeL) of Inria Centre at University of Lille in France. He teaches postgraduate-level courses on privacy, responsible machine learning, and research methods in AI at École normale supérieure-PSL University, Université de Lille, and Centrale Lille. He is also a member of the ELLIS Society (European Laboratory for Learning and Intelligent Systems) and the Paris unit of ELLIS. Dr. Basu earned his PhD in Computer Science from the Department of Computer Science, School of Computing, National University of Singapore, advised by Stéphane Bressan and Pierre Senellart. Prior to that, he obtained a B.E. degree with Honours in Electronics and Telecommunication Engineering from Jadavpur University. Before joining Inria, he was a postdoctoral researcher at Chalmers University of Technology's Data Science and AI Division. Dr. Basu's research focuses on constructing algorithms for developing efficient, robust, private, and ethical learning machines that solve real-world problems. His methodological approach blends statistics, machine learning, and optimization. His application interests span sustainable agro-ecology, medical and pharmaceutical applications, energy-efficient autonomous systems, and algorithmic audits. Recent collaborations include the Inria-Indian Statistical Institute associate team SeRAI for developing Sequential Testing and Learning Algorithms for Verifiably Robust and Responsible AI, and the Inria-INRAE collaboration on Resilient Agricultural Decision Making under Environmental Risks. His publication record demonstrates expertise in bandit algorithms, reinforcement learning, and privacy-preserving machine learning. Recent work shows a strong theoretical foundation with practical applications, particularly in pure exploration bandits, differential privacy mechanisms, constrained optimization, and fairness verification. His research bridges the gap between theoretical guarantees and real-world deployment challenges across multiple domains. Dr. Basu has received notable recognition for his contributions: Best Student Paper Award at ACM EAAMO 2022 for 'On Meritocracy in Optimal Set Selection' Young researcher (JCJC) grant from the French National Research Agency (ANR) in 2022 in 'Artificial Intelligence and Data Science' He leads the project 'RL under Real-life Constraints: Regrets and Algorithms' and supervises PhD students and postdoctoral researchers. His research is supported by multiple projects including REPUBLIC ('Vers l'IA responsable avec l'apprentissage par renforcement sous contraintes') and 'Foundations of robustness and reliability in artificial intelligence.' Dr. Basu actively collaborates with institutions worldwide, including establishing the RELIANT associate team with Kyoto University for investigating structured multi-armed bandit problems.

Ralf HerbrichView profile

Professor

• Approximate Computing
• Bayesian Inference and Decision Making
• Game Theory
• +14 more

Ralf Herbrich serves as Professor of Computer Science at the University of Potsdam and Hasso Plattner Institute (HPI) since 2022, chairing the Artificial Intelligence and Sustainability research group. With 25 years of combined industry and academic experience, he previously held research leadership roles at Microsoft, Facebook, Amazon, and Zalando. His educational foundation includes a Diploma in Computer Science (1997) and PhD in Theoretical Statistics (2000), both from Technical University of Berlin. Herbrich's research spans 17 interconnected AI domains: Approximate Computing Bayesian Inference and Decision Making Game Theory Information Retrieval Natural Language Processing Computer Vision Distributed Systems Learning Theory Knowledge Representation and Reasoning Computer Gaming Computational Advertising Recommender Systems Network Science Battery Management Kernel Methods Knowledge Bases Machine Learning Theory He champions a people-first methodology emphasizing real-world problem solving through 'working backwards' and 'customer-obsession', with over 80 peer-reviewed publications across these fields. His leadership prioritizes researcher development over project outcomes and favors scientific dialogue over solitary study. Herbrich actively mentors researchers within his AI and Sustainability group but specific advisee names aren't documented in source materials. His team focuses on applying rigorous research to large-scale sustainability challenges through principled engineering approaches.

• Bayesian Methods
• Stochastic Processes
• Time Series Analysis
• +3 more

Tevfik Aktekin is a Professor in the Department of Decision Sciences at the Paul College of Business and Economics, University of New Hampshire. His research focuses on Bayesian inference and stochastic modeling in service systems and business analytics. Education : Ph.D. in Decision Sciences (George Washington University), M.B.A. in Management Decision Making (George Washington University), B.S. in Mechanical Engineering (Yildiz Technical University). His work applies Bayesian state-space models to multivariate count data, with applications in call center staffing, product modification cycles, and public health analysis. He has published in journals like Annals of Applied Statistics , Bayesian Analysis , and European Journal of Operational Research . The 15 most recent articles highlight trends in sequential Bayesian learning for dynamic systems (e.g., bike-sharing, web traffic), time series of non-Gaussian data, and stochastic optimization under uncertainty. These works bridge statistical theory with practical applications in business and health.

• Civil Engineering
• Climate Science
• Machine Learning
• +6 more

Brennan Bean is an Assistant Professor in the Mathematics and Statistics Department at Utah State University's College of Arts & Sciences. His work focuses on geospatial modeling, statistical methods for extreme weather analysis, and machine learning applications in structural and environmental engineering. Recent publications highlight expertise in snow load prediction, Bayesian entropy, and interdisciplinary data science. Notable contributions include optimizing design methods for insulated concrete wall panels and addressing deployment challenges for ML models in engineering contexts. Research trends span geospatial data integration, climate change impact assessments, and educational interventions in STEM. Key subfields include ground snow load mapping, extreme value statistics, climate downscaling, and high-dimensional ecological modeling.

Drazen PrelecView profile

Professor

• Behavioral Economics
• Neuroeconomics
• Decision-Making Psychology
• +5 more

Drazen Prelec is a Professor of Management Science and Economics at the MIT Sloan School of Management , with appointments in the Department of Economics and Department of Brain and Cognitive Sciences . His work bridges psychology, neuroscience, and economics to study decision-making mechanisms. Education: AB in Applied Mathematics (Harvard College), PhD in Experimental Psychology (Harvard University) Prelec's research focuses on behavioral economics and neuroeconomics , particularly in areas like risky choice, time discounting, self-control, and consumer behavior. He develops normative decision theory while investigating its empirical limitations using behavioral and fMRI methods. Two major projects include: Self-Signaling : Examines non-causal motivation where individuals favor actions diagnostic of favorable outcomes over causal ones Bayesian Truth Serum : Creates scoring systems to reward honest judgments in domains without objective truth criteria His recent publications span topics in crowd wisdom , temporal discounting , and neuroeconomic modeling , with applications to consumer neuroscience, political forecasting, and behavioral ethics. Guggenheim Fellowship Junior Fellow, Harvard Society of Fellows Prelec contributes to understanding how credit card usage activates brain reward centers to increase spending, and explores honesty biases in social interactions. His work integrates computational models with empirical neuroscience to address foundational questions in decision theory.

• Numerical Analysis
• Uncertainty Quantification
• Inverse Problems
• +3 more

Oliver G. Ernst is a Professor of Numerical Analysis at Technische Universität Chemnitz . His research focuses on Numerical Analysis , Uncertainty Quantification , and Inverse Problems , with applications in Thermo-Hydro-Mechanical (THM) processes , Electromagnetics , and Stochastic Partial Differential Equations . He is associated with the Numerical Analysis group at TU Chemnitz. Key Research Areas : Efficient numerical methods for PDEs Krylov subspace techniques Stochastic finite element methods Multi-physics modeling Geoscientific applications Recent Publications (2025-2010): THM simulations under uncertainty Neural network PDE solvers Bayesian inversion frameworks Rational Krylov algorithms Deflated restarting strategies Collaborations : TU Bergakademie Freiberg University of Manchester Technical University of Munich University of Maryland University of Geneva Software Development : Contributor to OpenGeoSys platform Developer of FEMALY MATLAB library Academic Recognition : h-index 32, i10-index 66, with over 4423 citations since 2020.

Jan RatajView profile

Professor

• Integral Geometry
• Geometric Measure Theory
• Stochastic Geometry
• +2 more

Jan Rataj is a Professor at the Faculty of Mathematics and Physics , Charles University , specializing in Integral Geometry , Geometric Measure Theory , and Stochastic Geometry . He has been affiliated with Charles University since 1991 and has held visiting positions at universities in Jena, Karlsruhe, Ulm, and Aarhus. Research interests focus on geometric probability, convex geometry, and measure theory Teaches courses on Measure and Integration Theory , Geometry , and advanced topics in geometric measure theory Scientific contributions include coauthoring 2 monographs and ~50 research papers. His work explores: Random measurable sets and perimeter analysis Stochastic modeling of microstructures Geometric functionals and invariants Applications to spatial statistics and probability theory He supervises PhD students and leads the Seminar of Stochastic Geometry , which examines topics like: Max-stable random fields Convex body reconstruction Point process analysis

Olga MaslovskayaView profile

Associate Professor

• Survey Methodology
• Data Quality
• Survey Data Collection
• +3 more

Dr. Olga Maslovskaya serves as an Associate Professor in Survey Research and Social Statistics at the University of Southampton within the Faculty of Social Sciences, Department of Social Statistics and Demography. She is a prominent Survey Methodologist specializing in data quality and survey data collection methodologies. As Principal Investigator of the Survey Data Collection Network (SDC-Net), she leads research on the impact of COVID-19 on survey methodologies and previously directed the GenPopWeb2 international network focused on transitioning to online data collection. Her research interests center on all aspects of survey methodology with particular emphasis on data quality, survey data collection techniques, non-probability-based surveys, and mixed-mode survey design. She has made significant contributions to understanding smartphone survey effects, response propensity modeling, and the development of online survey methodologies for demographic research. Analysis of her recent publications reveals a strong focus on methodological innovations in survey research, particularly examining data quality across different survey modes, developing advanced statistical techniques for addressing nonresponse, and advancing online survey design for demographic studies. Her work frequently addresses practical challenges in contemporary survey methodology while maintaining rigorous statistical standards. Dr. Maslovskaya has secured substantial research funding through multiple ESRC grants for projects including the Generations and Gender Survey in the UK and the Survey Data Collection Network. She serves as a Co-Investigator on major ESRC-funded initiatives and leads methodological workpackages for national survey implementations. She currently supervises PhD students Ni Kadek Oki Wahyu Krisnadevi and Norizan Abdullah in the Social Statistics and Demography program. Her external professional engagements include membership on the editorial board of the Journal of Survey Statistics and Methodology (2020-2024), active participation in the Royal Statistical Society (2018-2024), and membership in the European Survey Research Association (2021-2025). As a member of the Statistical Sciences Research Institute (S3RI), Dr. Maslovskaya contributes to the Methodological Innovation: Survey Methods and Official Statistics research group. Her current projects examine underrepresented population subgroups in surveys, patient perspectives on health data collection, and continuing research on survey data collection methods in the post-pandemic era.

• Probability Theory
• Futurology
• Existential Risk
• +4 more

Olle Häggström is a Professor of Mathematical Statistics at Chalmers University of Technology, specifically in the Department of Applied Mathematics and Statistics. His academic career spans several decades with a significant shift in research focus over time. Häggström's research interests have evolved from traditional probability theory to encompass broader future-oriented topics. Initially focused on mathematical statistics and probability theory, including percolation theory and stochastic processes, he has increasingly turned his attention to futurology, existential risk, and AI safety in recent years. His work demonstrates a unique interdisciplinary approach, bridging rigorous mathematical analysis with philosophical considerations about humanity's technological trajectory. The trends in Häggström's publications reveal a clear evolution from purely mathematical research toward interdisciplinary studies examining the societal implications of emerging technologies. His recent work focuses heavily on AI safety, existential risk assessment, and long-term futures thinking, while still maintaining connections to his mathematical foundations. This shift is evident in publications ranging from technical mathematical papers to broader philosophical discussions about technology's impact on civilization. Häggström has received research funding from notable sources including the FTX Foundation Future Fund for his project "Topics in the theory of xrisk and longtermism" (2022-2025), indicating recognition of the importance of his work in the existential risk community. His book "Here Be Dragons: Science, Technology and the Future of Humanity" (2016) represents a significant synthesis of his thinking on these topics. While specific details about his advising activities are not provided in the source material, his research projects suggest engagement with interdisciplinary teams working at the intersection of mathematics, computer science, and future studies. His work appears to influence both academic and policy discussions regarding technological risk and long-term planning.

Erik Henning ThiedeView profile

Assistant Professor

• Theoretical Chemistry
• Computational Chemistry
• Machine Learning in Chemistry
• +11 more

Erik Henning Thiede is an Assistant Professor of Chemistry at Cornell University, affiliated with the Department of Chemistry and Chemical Biology. He joined the faculty in Summer 2023 and leads the Thiede Lab, which focuses on understanding protein motion and function through computational tools that integrate machine learning, molecular simulation, and chemical physics. PhD in Chemistry from the University of Chicago (advised by Profs. Aaron Dinner and Jonathan Weare) Postdoctoral Research at Flatiron Institute CCM (collaborating with Prof. Risi Kondor, Dr. Pilar Cossio, and Dr. Sonya Hanson) The lab's research spans several key areas: Developing algorithms to extract free energies from cryo-EM data Creating permutation-equivariant machine learning models for chemical systems Improving error estimation in molecular simulation frameworks like MBAR Applying Wasserstein flows and probabilistic methods to cryo-EM analysis Expanding cryo-EM capabilities for disordered protein regions Integration of experimental data with computational simulations His lab's publications highlight trends in computational chemistry, including the application of graph neural networks, Bayesian inference, and advanced statistical methods to molecular dynamics. These works bridge chemical physics, machine learning, and structural biology. As an academic advisor, Thiede mentors a diverse group of graduate students and postdoctoral researchers. His lab actively collaborates with interdisciplinary teams across Cornell and other institutions, with current projects involving chemical engineering, applied mathematics, and biophysics. The Thiede Lab at Cornell is committed to open and inclusive science. Values include curiosity, openness to new ideas, mutual support in research, and active inclusion of diverse backgrounds. The lab occupies space at 214 Baker Lab and maintains a research website at thiedelab.github.io .