Find Academic Supervisors

• Numerical Analysis
• Uncertainty Quantification
• Computational Mechanics
• +5 more

Prof. Raul Fidel Tempone is a renowned expert in Numerical Analysis and Uncertainty Quantification (UQ) at RWTH Aachen University, where he established the Lehrstuhl für Mathematics for Uncertainty Quantification . His research focuses on developing efficient numerical methods for stochastic models and differential equations, driven by applications in computational mechanics, quantitative finance, biological/chemical modeling, and wireless communication. Research emphasizes a posteriori error estimation, adaptive algorithms, Bayesian model calibration/validation, and optimal experimental design. Key contributions include multilevel Monte Carlo (MLMC) methods, hierarchical/sparse approximation, stochastic optimization, and machine learning integration for UQ. Recent work includes advancements in: MLMC for PDEs/SDEs and McKean-Vlasov equations Bayesian experimental design with nuisance parameters Uncertainty quantification in porous media and wireless networks Machine learning-based segmentation and filtering techniques He has advised numerous PhD/Master’s students and collaborates widely, producing over 150+ publications in top journals/conferences. His applied research bridges theoretical developments with real-world challenges in engineering, finance, and data science.

• Machine Learning
• Probabilistic Numerics
• Bayesian Inference
• +5 more

Philipp Hennig is a Full Professor (W3) at the Department of Computer Science, Eberhard Karls University Tübingen, heading the Chair for Methods of Machine Learning. He previously held positions at the Max Planck Institute for Intelligent Systems, including Emmy Noether Group Leader and Max-Planck-Group Leader. His research focuses on probabilistic numerics, Bayesian inference, and uncertainty quantification, with contributions to machine learning theory and computational methods. He co-founded the field of probabilistic numerics and authored the textbook Probabilistic Numerics — Computation as Machine Learning (2022). Education: PhD in Physics from the University of Cambridge (2007), MSci in Physics from Heidelberg University (2007). Research support includes DFG Emmy Noether Programme grants, ERC Starting/Consolidator Grants, and Max Planck Society funding. He leads the ELLIS Program on Theory, Algorithms, and Computations of Modern Learning Systems and serves as Dean of Studies for Tübingen's Computer Science Department. Key research directions include probabilistic ODE/PDE solvers, Bayesian deep learning, and uncertainty-aware algorithms. His work bridges computational methods with statistical inference, emphasizing scalable and theoretically grounded approaches. Recent projects address neural operator learning, uncertainty quantification in climate models, and efficient Gaussian process methods. Awards include ELLIS Fellowship and ERC grants. Over 100 publications span top venues like NeurIPS, ICML, and JMLR. Active in academic leadership roles, he co-leads the Tübingen AI Center and Cluster of Excellence for Machine Learning in Science. His lab develops open-source tools like ProbNum for probabilistic numerical computing.

Geoff NichollsView profile

Associate Professor

• Bayesian Inference
• Computational Statistics
• Monte Carlo Methods
• +4 more

Geoff Nicholls is an Associate Professor of Statistics at the University of Oxford, affiliated with St Peter's College as a Fellow and Tutor. He holds a B.Sc. in Physics from the University of Canterbury (New Zealand) and a PhD in High-Energy Physics from the University of Cambridge. His research focuses on Bayesian inference, computational statistics, and Monte Carlo methods applied to interdisciplinary problems in geoscience, linguistics, genetics, and archaeology. Notable contributions include semi-modular Bayesian inference frameworks and embedded diachronic sense change models for ancient languages. He has advised students like Lorenzo Pacchiardi and Jessie Jiang, and collaborates on tools like the TraitLab package for binary tree-like data analysis. Key research areas include statistical methods for partial orders, biclustering forensic data, and scalable Bayesian techniques for high-dimensional problems. His work bridges theoretical developments with practical applications, such as modeling historical power dynamics using 12th-century documents and analyzing linguistic evolution in ancient Greek texts.

• Mathematical Statistics
• Applied Probability
• Machine Learning
• +5 more

Mikolaj Kasprzak is an Assistant Professor at ESSEC Business School, specializing in mathematical statistics and applied probability. He holds a DPhil (PhD) in Statistics from the University of Oxford, following a Master’s degree in Mathematics, Operational Research, Statistics, and Economics from the University of Warwick. His career includes postdoctoral research at the University of Luxembourg and a Marie Skłodowska-Curie Individual Fellowship (2021–2023), with research stints at MIT and UCL. He joined ESSEC in 2024 as part of the Information Systems, Data Analytics, and Operations department. Research Interests: Mikolaj focuses on rigorously quantifying the accuracy of approximations in applied probability, statistics, and machine learning. His work involves developing mathematical tools to bound distances between probability distributions, with applications in Stein’s method, U-statistics, and stochastic processes. He emphasizes theoretical foundations while addressing real-world challenges in statistical inference and computational methods. Key Contributions: His research spans functional central limit theorems, kernel Stein discrepancies, and validated variational inference. Recent work includes advancements in goodness-of-fit tests for high-dimensional measures and error bounds for Bayesian posterior approximations. Awards: Marie Skłodowska-Curie Fellowship (2021), New Researcher Travel Award (2019), EUTOPIA Young Leaders Academy Fellowship (2024). Grants: Junior Chair of Excellence in Data Analytics (CY Initiative, 2024). Academic Roles: He also holds the Chaired Professorship in Data Science at ESSEC (2024–2028). His research has been published in top journals like Bernoulli , Annals of Applied Probability , and Probability Theory and Related Fields .

• Applied Mathematics
• Approximation Theory
• Orthogonal Polynomials
• +5 more

Darío Ramos López is a Professor of Applied Mathematics at the Department of Mathematics, Universidad de Almería (UAL). He coordinates the Double Degree in Economics and Mathematics and teaches subjects such as Mathematics II and Numerical Methods and Optimization . His research focuses on Approximation Theory, Orthogonal Polynomials, Bayesian Networks, and Machine Learning applications in biomedical optics and data streams. He leads the research group on Approximation Theory and Orthogonal Polynomials (FQM229). His work integrates mathematical modeling with real-world applications, including corneal data analysis (via the rPACI R package) and environmental conservation projects. He developed the AMIDST toolbox , a Java library for scalable probabilistic machine learning, supporting analysis of massive data streams in finance and other domains. He has authored over 30 publications since 2010, with recent contributions to nonstationary data stream inference and keratoconus detection using Bayesian methods. Tutoring sessions are held in-person or online at CITE III INFORMATICA-MATEMAT (Office 1-400), with flexible scheduling via email appointment.

Edriss S. TitiView profile

Professor

• Nonlinear Dynamical Systems
• Fluid Dynamics
• Mathematical Physics
• +3 more

Edriss S. Titi is a Professor in the Department of Applied Mathematics and Theoretical Physics (DAMTP) at the University of Cambridge. His research focuses on nonlinear dynamical systems, fluid dynamics, and mathematical physics, with particular emphasis on geophysical fluid dynamics, partial differential equations, and data assimilation. Titi's work addresses fundamental questions in ocean and atmospheric modeling, turbulence, and climate systems. He has contributed extensively to the mathematical analysis of equations such as the Navier-Stokes, Euler, and primitive equations, exploring their well-posedness, regularity, and numerical treatment. His recent research includes studies on the hydrostatic approximation limit, energy conservation in fluid flows, and the application of machine learning to data assimilation in chaotic systems. Titi collaborates with international teams to develop advanced models for climate prediction and ocean dynamics, incorporating eddy parametrization and multiscale analysis techniques. Key areas of focus include: Global well-posedness of geophysical fluid models Non-uniqueness and admissibility of weak solutions Machine learning-enhanced data assimilation Mathematical analysis of turbulence and boundary layers

Samuel BerchuckView profile

Assistant Professor

• Machine Learning
• Biostatistics
• Glaucoma Research
• +4 more

Samuel Berchuck is an Assistant Professor in the Department of Biostatistics & Bioinformatics at Duke University, with a joint appointment in Statistical Science at Trinity College of Arts & Sciences. He is also a member of the Duke Cancer Institute and affiliated with Duke AI Health and the Visual Performance Lab at Duke Eye Center. His research focuses on developing machine learning and statistical methods to address critical challenges in healthcare, particularly in glaucoma, autism spectrum disorder, and oncology. He holds a Ph.D. in Biostatistics from the University of North Carolina-Chapel Hill and completed an NIH K99/R00 postdoctoral fellowship at Duke. Education: Ph.D. in Biostatistics, University of North Carolina, Chapel Hill (2018). Research Interests: Machine learning for healthcare prediction and decision support Statistical modeling of longitudinal spatiotemporal data Integration of electronic health records and clinical narratives Psychosocial distress screening in ophthalmology Bayesian methods for small sample and complex data Grants: NIH K99/R00 Postdoctoral Fellowship (National Eye Institute) Development of an AI-driven glaucoma care program (National Eye Institute, 2024–2027) Spatiotemporal cancer care patterns study (Medical College of Wisconsin, 2025) Labs/Teams: Duke AI Health, Visual Performance Lab (Duke Eye Center), and collaborations with the Duke Glaucoma Registry.

Ullrich KötheView profile

Associate Professor

• Machine Learning
• Neural Networks
• Explainable AI
• +6 more

Prof. Dr. Ullrich Köthe is an Associate Professor and group leader in the Visual Learning Lab Heidelberg at the University of Heidelberg . He focuses on Explainable Machine Learning , leveraging Invertible Neural Networks to enhance transparency and utility in image analysis and medical applications . He also maintains the widely used VIGRA image analysis library. Education: PhD in Informatics, University of Hamburg, 2000 Habilitation in Informatics, University of Hamburg, 2008 His research interests center around machine learning , image analysis , and scientific computing , particularly the development of robust algorithms for medical imaging , computer vision , and life sciences . His work on invertible neural networks and parameter-free segmentation has led to significant advancements in the field. Recent publications highlight his contributions to Bayesian inference , neural network interpretability , and stochastic modeling , with applications ranging from disease outbreak dynamics to connectomics . Key trends include generative models , parameter-free segmentation , and likelihood-free inference . Scientific Awards: DAGM 2003 Main Prize DAGM Best Paper Award 2008 He has supervised numerous Master and Bachelor theses in machine learning and image analysis , with teaching roles in Advanced Machine Learning and Explainable AI . His collaborative research grants include funding from HARMAN International (2024). He leads the Explainable Machine Learning subgroup and has contributed to open-source software projects like ilastik and VIGRA , which are critical tools in bioimage analysis .

Jean-Jacques ForneronView profile

Assistant Professor

• Econometrics
• Macroeconometrics
• Industrial Organization
• +3 more

Jean-Jacques Forneron is an Assistant Professor of Economics at Boston University, specializing in econometrics and computational methods. He holds a PhD from Columbia University (2018), an MA in Economics and Statistics from ENSAE Paris (2012), and an MSc in Management from HEC Paris (2012). His research focuses on advancing econometric theory, particularly in dynamic models, moment condition estimation, and stochastic optimization techniques. He explores topics like model misspecification, optimal transportation approaches, and robust estimation under noisy conditions. His recent work emphasizes methodological innovations in simulation-based estimation, including sieve estimators, scrambled methods of moments, and likelihood-free sampling. These contributions aim to address challenges in parameter identification, computational efficiency, and statistical inference under non-standard conditions. Forneron teaches advanced econometrics courses at both MA and PhD levels, including Advanced Econometrics 2 and Advanced Topics in Econometrics , often co-instructing these courses. His office is located in SSW 415D on Boston University's campus.

Maryclare GriffinView profile

Assistant Professor

• Statistical Inference
• Time Series Analysis
• Variable Importance
• +3 more

Maryclare Griffin is an Assistant Professor in the Department of Mathematics and Statistics at the University of Massachusetts Amherst. Her research develops statistical methods for complex data analysis, with emphasis on time series modeling, variable importance measures, Bayesian computation, and interpretable machine learning. Current methodological work includes adaptive overdifferencing for non-stationary processes, mixture representations for Bayesian simulation, and structured shrinkage priors for high-dimensional inference. Applications span clinical genomics, environmental monitoring, and biophysical trend analysis. Recent publications demonstrate innovations in time series model identification, optimization algorithms for regularized regression, and variable importance frameworks for nonlinear models. Collaborative work extends to metastasis prediction in melanoma and lightning strike pattern modeling. Holds a PhD in Statistics from the University of Washington and completed postdoctoral training at Cornell's Center for Applied Mathematics. Maintains active research in computational statistics and model interpretability.

• Survey Methodology
• Multilevel Modelling
• Poststratification
• +3 more

Dr Lauren Kennedy is a Lecturer at the University of Adelaide's School of Computer and Mathematical Sciences, Department of Mathematical Sciences. Her research focuses on survey methodology, multilevel modeling, poststratification, causal inference, and Bayesian statistical techniques. She specializes in addressing challenges arising from non-representative data and improving inference in social sciences through advanced statistical methods. Her work emphasizes practical applications in public opinion analysis, epidemiological modeling, and policy evaluation. Dr Kennedy is actively involved in supervising postgraduate students in Masters and PhD programs, particularly as a co-supervisor. She maintains an office in 6.56 Ingkarni Wardli Building on North Terrace campus and can be contacted at lauren.a.kennedy@adelaide.edu.au . Key research contributions include innovations in Bayesian workflow, cross-validation methodologies, and the integration of machine learning with traditional survey techniques. Her recent publications highlight advancements in causal inference frameworks and hierarchical modeling approaches for large-scale datasets.

Robert BeinertView profile

Senior Lecturer

• Applied Mathematics
• Inverse Problems
• Optimal Transport
• +3 more

Robert Beinert is a Senior Lecturer (Privatdozent) in Applied Mathematics at the Technische Universität Berlin, affiliated with the Department of Applied Mathematics within the Faculty of Mathematics and Natural Sciences. He holds a Dr. rer. nat. (Ph.D.) from Georg-August-Universität Göttingen (2015) and completed his Habilitation at Technische Universität Berlin in 2025. His research focuses on inverse problems, optimal transport, phase retrieval, and mathematical imaging, with applications in signal processing and data analysis. He has held academic positions including Research Associate roles at TU Berlin (2020–2025), Karl-Franzens-Universität Graz (2016–2020), and Georg-August-Universität Göttingen (2016). His work bridges theoretical foundations and practical applications, with contributions to regularization techniques, optimal transport theory, and algorithmic development. Key research interests include phase retrieval uniqueness analysis, Gromov-Wasserstein transport, and denoising methodologies for manifold-valued data. His recent publications emphasize advancements in optimal transport frameworks, regularization strategies, and applications in image processing and machine learning.

• Bayesian computations
• Posterior simulation methods
• Econometric and statistical methods
• +7 more

David Gunawan is a Senior Lecturer in Statistics at the School of Mathematics and Applied Statistics, University of Wollongong. He holds a PhD from Monash University and specializes in Bayesian computational methods, bridging methodological development and real-world applications in economics, health, and environmental sciences. His research focuses on posterior simulation techniques (e.g., MCMC, SMC, ABC) and applies these to problems like economic inequality measurement, health outcomes analysis, and offshore engineering challenges. He has secured significant funding from the Australian Research Council (ARC) and other bodies, including leadership in projects on energy infrastructure digitalization and cognitive model inference. Gunawan supervises multiple PhD/Master’s students on topics ranging from wave prediction algorithms to socioeconomic inequality analysis. His work integrates machine learning with traditional statistical methods, exemplified by contributions to phase-resolved wave modeling and spatial statistics. He collaborates with the National Institute for Applied Statistics Research Australia (NIASRA) and maintains a Google Scholar profile at bit.ly/2Gi1PVy .

Denis BelomestnyView profile

Professor

• Statistics of Stochastic Processes
• Financial Mathematics
• Econometrics
• +5 more

Denis Belomestny is a Professor of Applied Stochastics at the Department of Mathematics, University of Duisburg-Essen. His academic journey includes a PhD from Lomonosov Moscow State University (2002), postdoctoral work at the University of Bonn, and research positions at WIAS Berlin and Humboldt University Berlin. He currently leads research at the intersection of stochastic processes and financial mathematics. PhD in Mathematics, Lomonosov Moscow State University (2002) W3 Professorship in Applied Stochastics, University of Duisburg-Essen (2011–present) His research focuses on statistics of stochastic processes , optimal stopping/control , and Monte Carlo methods , with applications in financial mathematics and machine learning. Key collaborations include work with John Schoenmakers on multilevel approximation algorithms and Alexey Naumov on variance reduction techniques. Recent publications (2025–2023) explore deep neural networks for SDEs , generative adversarial networks , and nonparametric estimation in complex stochastic models. His work spans stochastic differential equations , financial derivatives pricing , and machine learning-driven statistical inference . He supervises doctoral students, including Sascha Nolte (research: robust optimal stopping without reference models). Current projects involve McKean-Vlasov SDEs , gamma-driven processes , and reinforced optimal control .

Patrick LaubView profile

Senior Lecturer

• Actuarial Science
• Data Science
• Artificial Intelligence
• +3 more

Patrick Laub is a Senior Lecturer at the UNSW School of Risk and Actuarial Studies, where he teaches courses in artificial intelligence and machine learning with a focus on risk and insurance applications. His academic work bridges the gap between advanced computational methods and practical actuarial problems. Patrick holds a joint PhD in computational applied probability completed between the University of Queensland and Aarhus University. He also possesses degrees in software engineering and mathematics, providing him with a strong interdisciplinary foundation for his research. His research focuses on computationally challenging problems in actuarial data science, with particular emphasis on natural catastrophe modeling and artificial intelligence applications. Key areas of investigation include Hawkes processes for modeling contagion in insurance claims, Approximate Bayesian Computation for fitting complex insurance loss models, and Empirical Dynamic Modeling for analyzing complex temporal dependencies. His work addresses critical challenges in risk assessment, particularly for extreme events where traditional statistical methods may be inadequate. Analysis of Patrick's recent publications reveals a strong trend toward integrating advanced statistical methodologies with practical actuarial applications. His work spans from theoretical developments in point processes and Bayesian inference to practical implementations in computational environments. A notable theme is the application of machine learning techniques to traditional actuarial problems, particularly in the areas of catastrophe modeling and risk prediction. Patrick has developed and taught innovative courses since 2022, including 'Artificial Intelligence & Deep Learning and their Applications to Risk and Insurance' (ACTL3143 and ACTL5111) and 'Statistical Machine Learning for Risk and Actuarial Applications' (ACTL5110). These courses reflect his commitment to preparing students for the evolving landscape of data-driven risk management in the insurance industry. His research is supported by UNSW's strong infrastructure for computational research, though specific lab affiliations are not explicitly mentioned in the available information. Patrick maintains an active research program with numerous publications across statistics, actuarial science, and computational methods.