Find Academic Supervisors

Yen-Chi ChenView profile

Associate Professor

• Nonparametric statistics
• Topological data analysis
• Missing data
• +7 more

Yen-Chi Chen is an Associate Professor in the Department of Statistics at the University of Washington. He also holds positions as a Data Science Fellow at the UW eScience Institute and as a co-investigator and statistician at the National Alzheimer's Coordinating Center. His academic career spans multiple interdisciplinary fields including statistics, data science, and astrostatistics. Chen's educational background includes a Ph.D. from Carnegie Mellon University, where he received prestigious awards including the Umesh K. Gavasakar Thesis Award (2017) and the William S. Dietrich II Presidential Ph.D. Fellowship Award (2015). His research focuses on nonparametric statistics, topological data analysis, missing data methodologies, cluster analysis, manifold learning, and applications in large-scale structure analysis and astrostatistics. Chen has made significant contributions to the development of statistical methods for analyzing cosmic web structures, GPS data, and causal inference with continuous treatments. His work bridges theoretical statistics with practical applications in astronomy, neuroscience, and public health. Analysis of his recent publications reveals a strong emphasis on developing novel statistical frameworks for complex data structures, particularly focusing on density-based methods, manifold learning, and approaches that address challenges in missing data and causal inference without standard assumptions. ASA Noether Early Career Scholar Award, American Statistical Association (2022) CAREER Award, National Science Foundation (2022-2027) Umesh K. Gavasakar Thesis Award, Carnegie Mellon University (2017) William S. Dietrich II Presidential Ph.D. Fellowship Award, Carnegie Mellon University (2015) Chen has advised numerous graduate students across multiple publications, with a focus on developing new statistical methodologies. His research has been supported by major funding agencies including the National Science Foundation and the National Institutes of Health. He is actively involved in several research groups including the UW Geometric Data Analysis Group, the UW Center for Statistics and the Social Sciences, and the National Alzheimer's Coordinating Center.

Slava JankinView profile

Professor

• Artificial Intelligence
• Machine Learning
• Natural Language Processing
• +3 more

Slava Jankin is a Professor of Data Science and Government at the University of Birmingham’s School of Government, where he also serves as Deputy Director of the Institute for Data and AI and Founding Director of the Centre for Artificial Intelligence in Government. He is concurrently a Fellow and Founding Director of the Data Science Lab at the Hertie School in Berlin. Previously, he held a Professorship at the University of Essex and has worked at University College London (UCL) and the London School of Economics (LSE). His research bridges computational methods, governance, and climate policy, with a focus on AI applications in public institutions, climate-health surveillance, and misinformation resilience. Jankin earned a PhD in Political Science from Trinity College Dublin (2009), a Postgraduate Diploma in Statistics (2006), and a BSc from Belarus State Economic University (2002). **Education**: • PhD in Political Science, Trinity College Dublin (2009) • Postgraduate Diploma in Statistics, Trinity College Dublin (2006) • BSc Econ with Distinction, Belarus State Economic University (2002) **Research Interests**: Jankin’s work integrates AI and computational methods with governance challenges, including climate policy, health surveillance, and institutional effectiveness. He leads initiatives like the Lancet Countdown’s climate-health monitoring and the CATALYSE project on climate impacts. His research also explores digital twins for governance systems and the role of cultural diversity in societal resilience against misinformation. **Grants & Collaborations**: He advises the UN and EU on AI and data science, co-leads the Lancet Countdown, and collaborates with institutions like the Alan Turing Institute. His applied work includes developing AI tools for public service optimization and policy simulations. **Labs & Teams**: Directs the Centre for AI in Government (University of Birmingham) and the Hertie School’s Data Science Lab, fostering interdisciplinary teams to advance computational methods in public policy.

• Fuzzy Systems
• Computational Intelligence
• Nonlinear Control
• +4 more

Michio Sugeno is a distinguished Professor at Tokyo Institute of Technology's Graduate School of Information Science and Engineering, Department of Computational Intelligence. With a career spanning over four decades, he has established himself as a leading figure in fuzzy systems and computational intelligence. His research interests encompass Fuzzy Systems, Computational Intelligence, Nonlinear Control, Choquet Integral theory, Brain-Computer Interfaces, and Linguistic Computing. Sugeno's work has fundamentally shaped modern fuzzy control theory, particularly through his development of the Takagi-Sugeno fuzzy model which has become a standard approach in industrial applications. Analysis of his recent publications reveals a continued focus on piecewise nonlinear modeling, stability analysis of fuzzy systems, and the application of Choquet calculus to various computational problems. His work demonstrates a consistent trajectory from theoretical foundations to practical implementations in control systems and intelligent computing. IEEE Pioneer Award in Fuzzy Systems IFSA Fellow Emanuel R. Piore Award Sugeno has mentored numerous researchers who have become prominent in their own right, including Tadanari Taniguchi, Luka Eciolaza, and Anh-Tu Nguyen. His laboratory has been instrumental in developing novel approaches to nonlinear control systems using piecewise bilinear models and fuzzy logic. Current research directions include brain-computer interfaces using EEG analysis and the development of everyday language computing systems that enable more natural human-computer interaction.

Volker J SchmidView profile

Professor

• Bayesian Statistics
• Spatial Statistics
• Medical Imaging
• +7 more

Volker J Schmid is a Professor of Bayesian Imaging and Spatial Statistics at the Department of Statistics, Ludwig Maximilian University of Munich. He leads the Bayesian Imaging and Spatial Statistics group and contributes to interdisciplinary initiatives like the Munich Center of Machine Learning. His work bridges statistical theory with applications in medical imaging and biology. PhD in Statistics (2004), LMU Munich Diploma in Statistics (2000), LMU Munich Abitur, Joseph-von-Fraunhofer-Gymnasium Cham (1993) His research focuses on Bayesian computational methods for high-dimensional data, particularly in medical imaging (MRI, DCE-MRI) and biological microscopy (e.g., 3D nuclear architecture analysis via super-resolution microscopy). Key applications include disease mapping , image segmentation , and spatio-temporal modeling . His software tools (e.g., nucim , bioimagetools , BAMP ) enable quantitative analysis in nuclear imaging and age-period-cohort modeling. His 15 most recent publications span Bayesian modeling for medical imaging , spatio-temporal epidemiology , and computational biology . Topics include co-localization metrics in fluorescence microscopy, nuclear architecture analysis, and dynamic Bayesian frameworks for MRI data. Collaborations extend to neuroimaging, oncology, and nuclear biology.

Christian WaldView profile

Research Fellow

• Generative Modeling
• Flow Matching
• Stochastic Processes
• +3 more

Christian Wald is a Post-doctoral researcher at Technical University Berlin working under Professor Gabriele Steidl, focusing on generative modeling, flow matching, and stochastic processes in machine learning. His research bridges theoretical probability with practical medical imaging applications, particularly in MRI reconstruction and analysis. He completed his PhD at Humboldt University of Berlin in 2017 with a thesis on p-adic quantum groups. His academic journey transitioned from pure mathematics to interdisciplinary machine learning research, reflecting his versatile expertise. Wald's primary research explores generative models through the lens of optimal transport and flow matching, with significant contributions to Wasserstein geometry and conditional distance metrics. His work frequently integrates stochastic processes to enhance medical image reconstruction, demonstrating strong cross-disciplinary impact in both theoretical machine learning and clinical applications. Recent publications highlight innovations in sliced MMD flows, Bayesian OT methods, and uncertainty-aware medical image analysis. Analysis of his 15 most recent publications (2019-2025) reveals a consistent trajectory toward unifying geometric probability with deep learning. Key themes include flow-based generative modeling for medical time-series data, optimal transport applications in image reconstruction, and novel kernel methods for distribution matching. His work spans both foundational theory (e.g., Fisher-Rao curves) and high-impact medical applications (e.g., coronary calcium scoring). No specific scientific awards are documented in the provided text, though his publications appear in prestigious venues including ICLR, IEEE TMI, and Physics in Medicine & Biology. Wald maintains extensive collaborations with the medical imaging group at Technical University Berlin, particularly with Andreas Kofler and Gabriele Steidl. His co-authored works demonstrate consistent contributions to MRI reconstruction pipelines and segmentation frameworks, though no formal advising roles or grant leadership are indicated. Current projects focus on uncertainty quantification in active learning for medical image segmentation. He operates within Gabriele Steidl's research group at Technical University Berlin, which specializes in mathematical imaging and machine learning. The team combines expertise in optimization, probability theory, and deep learning to solve medical imaging challenges, with Wald contributing core algorithmic innovations in generative modeling and stochastic reconstruction.

• Adaptive nonparametric statistics
• High-dimensional data analysis
• Financial time series modeling
• +5 more

Prof. Vladimir Spokoiny is a leading figure in stochastic algorithms and nonparametric statistics at the Weierstrass Institute for Applied Analysis and Stochastics (WIAS) and Humboldt University of Berlin . His work bridges mathematical statistics with practical applications in finance, medicine, and machine learning. Born in 1959 in Moscow, USSR PhD from Lomonosov Moscow State University (1988) Habilitation from Humboldt University (1996) Head of WIAS research group since 2000 Professor at Humboldt University since 2002 Spokoiny's research focuses on adaptive nonparametric methods, high-dimensional data analysis, and statistical finance. His innovations in local homogeneity testing and propagation-separation methods have advanced volatility modeling, image analysis, and manifold learning. He employs Bayesian optimization frameworks and stochastic control techniques for financial instrument pricing. Recent scientific contributions include generalized bootstrap procedures for Bures-Wasserstein barycenters (2024), dimension-free Laplace approximation bounds (2023), and structure-adaptive manifold estimation (2022). His 19+ PhD students and editorial roles in top journals like The Annals of Statistics demonstrate sustained academic impact. International Statistical Institute member American Statistical Association fellow Institute of Mathematical Statistics member Bernoulli Society member

Melanie SchienleView profile

Professor

• Econometrics
• Statistical Methods
• Financial Risk Analysis
• +4 more

Prof. Melanie Schienle is a Professor and Chair of Statistical Methods and Econometrics at the Department of Economics and Management, Karlsruhe Institute of Technology (KIT). She also holds a professorship in the Department of Mathematics at KIT since 2021. Her expertise spans statistical methods, econometrics, financial risk analysis, and forecasting. She leads the HKMetrics Network and the RespiNow Hub for respiratory disease forecasting. She serves as a Senior Fellow at the Rimini Center for Economic Analysis (RCEA), a steering committee member of the German Economic Association, and a member of the University Research Council at KIT. Education: Ph.D. (Dr. rer. pol.) in Economics from Mannheim University (2008), summa cum laude; Diploma in Mathematics (University of Karlsruhe, 2003) with a minor in theoretical physics. She has held academic positions at Leibniz University Hannover (2012–2015) and Humboldt University of Berlin (2008–2012). Research interests focus on financial networks, systemic risk, time series analysis, and machine learning applications in economics. She co-leads projects on nowcasting and forecasting, including collaborative efforts during the pandemic to predict hospitalizations. Her work integrates advanced statistical techniques with real-world policy implications. Prof. Schienle is an Associate Editor for the International Journal of Forecasting and Journal of Time Series Analysis . She has authored over 50 peer-reviewed publications and contributed to high-impact journals like Nature Communications and Journal of Business & Economic Statistics . She leads the Institute of Statistics at KIT and chairs the MathSEE initiative for interdisciplinary mathematical applications.

Daniel WilhelmView profile

Professor

• Econometrics
• Statistics
• Nonparametric Methods
• +4 more

Daniel Wilhelm is a Professor of Statistics and Econometrics at LMU Munich, with a courtesy appointment in the Department of Economics. His research focuses on econometric theory, nonparametric methods, measurement error modeling, and statistical inference. He leads the Statistics and Econometrics Group at LMU and holds affiliations with the Centre for Microdata Methods and Practice (CeMMAP), Institute for Fiscal Studies (IFS), and the Centre for Research and Analysis of Migration (CReAM). Wilhelm’s work includes groundbreaking contributions to NPIV estimation, robust statistical testing, and the development of R and Stata packages for rank inference and econometric analysis. His recent publications address topics like rank-based inference, measurement error detection, and high-dimensional independence testing. He organizes academic events such as the Munich Econometrics Seminar and the LMU-Todai Econometrics Workshop. His research emphasizes methodological rigor and practical applications, with a focus on improving statistical techniques for social science and policy analysis.

• Spatial Statistics
• Spatiotemporal Modeling
• Environmetrics
• +3 more

Philipp Otto is a Professor of Statistics and Data Science at the University of Glasgow. Previously, he was a Reader in Statistics and Data Analytics (2023–2024) and held a Junior Professorship in Big Geospatial Data at Leibniz University Hannover (2018–2023). He earned his PhD in Statistics (summa cum laude) from European University Viadrina in 2016 and a B.Sc. in International Economics, with study visits to Saint Petersburg State University. His research focuses on spatial and spatiotemporal statistics, environmetrics, network modeling, and machine learning applications. Education: PhD in Statistics (2016), European University Viadrina, Frankfurt (Oder) B.Sc. in International Economics (with study visits to Saint Petersburg) Research Interests: Philipp’s work centers on spatial statistics, spatiotemporal volatility modeling, environmental data analysis, and network processes. He develops statistical methods for geo-referenced and network data, with applications in climatology, finance, and environmental risk assessment. His contributions include advancements in GARCH models, spatiotemporal clustering detection, and statistical process monitoring for AI systems. Grants & Projects: He has secured €1,038,847 in research grants, leading projects on historical map time series analysis, agricultural air quality impacts, and high-dimensional spatial dependence structures. Industry collaborations include survival analysis for building information models. Awards: 2017 Fellowship to attend the Lindau Nobel Laureate Meeting (Economic Sciences) 2017 Best Presentation Award (Data Science, Statistics, and Visualisation) Teaching: He teaches statistics and data science across disciplines, including economics, engineering, and mathematics, at both undergraduate and postgraduate levels. Professional Activities: Editorial Boards: Environmetrics (2021), AStA Advances in Statistical Analysis (2020) Member of German Statistical Society (Treasurer, 2013)

Marco CuturiView profile

Professor

• Machine Learning
• Optimal Transport
• Optimization
• +4 more

Marco Cuturi is a Research Scientist at Apple ML Research in Paris and Professor of Statistics at CREST-ENSAE, Institut Polytechnique de Paris. His work bridges machine learning , optimal transport , and optimization , with applications in time-series analysis , kernels , and multiresolution methods . He has held academic roles at Kyoto University and Princeton University, and previously worked in the financial industry. Research Interests: Optimal transport theory and computational methods Kernel design for structured data and histograms Time-series alignment and soft-DTW Entropic regularization in optimization Applications to computer vision and genomics Teaching: Cuturi has taught courses on linear optimization at Princeton, geometric methods in machine learning at Kyoto, and scientific English. He has also organized machine learning summer schools in Kyoto, Les Houches, and other international venues. Recent Trends: His 2024-2025 publications focus on entropic optimal transport solvers, disentangled representation learning via Gromov-Monge gaps, and applications to text-to-image diffusion models. Collaborative work with institutions like Google Research, MIT, and University of Tokyo highlights his interdisciplinary impact.

• Business Process Management
• Process Mining
• Complex Event Processing
• +5 more

Prof. Dr. Matthias Weidlich is a faculty member at Humboldt University of Berlin within the Institute of Computer Science under the Faculty of Mathematics and Natural Sciences . His research focuses on Process Mining , Complex Event Processing , and Data Privacy with applications in Business Process Management and Scientific Workflows . Research Interests: Business Process Management and Process Mining Complex Event Processing and Stream Data Analysis Data Privacy and Security in Process Systems Scientific Workflow Systems and User Behavior Heterogeneous Network Embeddings Algorithm Design and Optimization Recent Publications (2023-2025) demonstrate expertise in: Efficient stream processing techniques Privacy-preserving process mining frameworks Scientific workflow analysis tools Graph neural network applications Multi-modal data integration Adaptive querying systems Contact: Office: Unter den Linden 6, 10099 Berlin Phone: 030 2093-41277 Email: matthias.weidlich@hu-berlin.de Web: hu.berlin/data

James Urquhart AllinghamView profile

Researcher

• Bayesian Deep Learning
• Deep Generative Models
• Probabilistic Methods in Machine Learning
• +7 more

James Urquhart Allingham is a Research Scientist at Google DeepMind , working on the Gemini project. He completed his PhD in the Machine Learning Group at the University of Cambridge under the supervision of José Miguel Hernández-Lobato, with funding from EPSRC, the Michael E. Fisher Studentship in Machine Learning, and the Qualcomm Innovation Fellowship. He was also part of the ELLIS PhD program, advised by Eric Nalisnick at AMLab UvA. Current affiliation: Google DeepMind (Research Scientist) PhD: University of Cambridge (Machine Learning Group) Academic networks: ELLIS PhD program, Darwin College His research focuses on the intersection of Bayesian deep learning and probabilistic methods in deep learning. Key areas include deep generative models , zero-shot classification , prompt engineering , Monte Carlo gradient estimation , and applications to sustainability and climate change . His work has explored energy-based models , neural architecture search , and equivariance in convolutional networks . Selected scientific awards and grants include the Michael E. Fisher Studentship , Qualcomm Innovation Fellowship , and MPhil in Advanced Computer Science with Distinction . He has collaborated with institutions such as the Amsterdam Machine Learning Group (AMLAB) and University of the Witwatersrand .

Mahsa GhasemiView profile

Assistant Professor

• Reinforcement Learning
• Control Theory
• Active Perception
• +3 more

Mahsa Ghasemi is an Assistant Professor in the Elmore Family School of Electrical and Computer Engineering at Purdue University, leading the AKADEMI Group. Her research focuses on theoretical advancements in trustworthy sequential decision-making for autonomous systems, emphasizing human-aware collaboration and adaptation to dynamic environments. She is affiliated with the Institute for Control, Optimization and Networks (ICON). Education: PhD in Electrical and Computer Engineering from The University of Texas at Austin (2021), MSE in Mechanical Engineering (2017), and BSc in Mechanical Engineering from Sharif University of Technology (2014). Research Interests: Reinforcement learning, control theory, active perception, multi-agent systems, robotics, and online learning. Applications span disaster response, healthcare, and autonomous systems design. Key methodological directions include compositional learning, human-AI collaboration, and adaptive decision-making under uncertainty. Teaching: Courses include Reinforcement Learning Theory (ECE 59500), Introduction to Reinforcement Learning (ECE 49595), and Python for Data Science (ECE 20875). Awards: Finalist for Student Best Paper Award at the 2018 American Control Conference (ACC). Students: Current advisees include Maheed H. Ahmed, Jayanth Bhargav, and Somtochukwu Oguchienti. Past members include Lai Wei and Juan Sebastian Mateo Ruiz Bulla. Service: Editorial roles at ICRA, ICCPS, and IFAC workshops. Reviewer for top conferences (NeurIPS, ICML) and journals (Automatica, IEEE TAC). Labs/Teams: Leads the AKADEMI Group, focusing on algorithmic and theoretical research in autonomous decision-making systems.

Charley WuView profile

Professor

• Computational Cognitive Science
• Human Learning Under Uncertainty
• Generalization and Inference
• +7 more

Charley Wu is an Independent Research Group Leader and W3 Professor of Computational Cognitive Science, currently transitioning from the University of Tübingen to Technische Universität Darmstadt. He leads the Human and Machine Cognition Lab (HMC Lab), jointly funded by the Excellence Cluster 'Machine Learning for Science' and the Tübingen AI Center, soon to be based at TU Darmstadt under a LOEWE Start Professorship and an ERC Starting Grant. University of Tübingen (former affiliation) Technische Universität Darmstadt (current/transitioning to) Human and Machine Cognition Lab (HMC Lab) Excellence Cluster 'Machine Learning for Science' Tübingen AI Center Charley Wu's research lies at the intersection of cognitive science and artificial intelligence, focusing on how humans learn and make decisions under uncertainty. Using computational models, statistical learning, and virtual reality experiments, he investigates the cognitive shortcuts and strategies people use to generalize and explore efficiently in complex environments. His work also explores social learning and collective intelligence through biologically inspired multi-agent systems. His recent publications, including a key paper in Nature Human Behaviour on generalization guiding exploration, reflect a strong trend toward integrating machine learning techniques with human behavioral data. The research emphasizes efficient inference, compressed representations, and compositional structures in cognition, bridging gaps between human and artificial intelligence. Notable scientific awards include: ERC Starting Grant: C⁴: Compositional Compression in Cognition and Culture LOEWE Start Professorship Dr. Wu is actively mentoring and expanding his research group, currently recruiting three fully-funded PhD students and one postdoctoral researcher. His lab is supported by competitive grants and institutional funding, indicating strong research momentum and future directions in computational models of cognition, AI-human alignment, and collective learning. He collaborates with leading researchers such as Fiery Cushman and Sam Gershman from his postdoctoral work at Harvard University. The Human and Machine Cognition Lab (HMC Lab) is a dynamic research environment focused on understanding the computational principles of human learning. As it transitions to TU Darmstadt, the lab will continue to explore fundamental questions in cognition using cutting-edge methodologies, including online experiments, multi-agent simulations, and AI-driven modeling.

Daniela M WittenView profile

Professor

• Statistical Machine Learning
• High-Dimensional Statistics
• Unsupervised Learning
• +5 more

Daniela M Witten is a Professor of Statistics and Biostatistics at the University of Washington, holding the Dorothy Gilford Endowed Chair in Mathematical Statistics. Her research focuses on developing statistical machine learning methods for high-dimensional data, with a particular emphasis on unsupervised learning and theoretical foundations. Witten earned her BS in Math and Biology with Honors and Distinction from Stanford University in 2005 and her PhD in Statistics from Stanford University in 2010 under Robert Tibshirani. Her academic journey established her expertise in bridging mathematical theory with biological applications. Her research program centers on high-dimensional statistical learning , where she develops methods for unsupervised learning and graphical modeling when features outnumber observations. She pioneers statistical models for neural activity through collaborations with the Allen Institute for Brain Science and Princeton University, addressing functional connectivity and neuron sub-population identification. Her groundbreaking work on selective inference solves the "double-dipping" problem in hypothesis generation and testing, enabling valid inference after hierarchical clustering and regression trees. Additionally, she advances multi-view data analysis to integrate complementary data sources like clinical and genomic measurements. Applications span genomics, neuroscience, microbial ecology, and pathology, demonstrating her commitment to solving real-world biomedical challenges. Her 2025 publications reveal a cohesive trend toward developing theoretically rigorous inference frameworks for high-dimensional settings, with emphasis on linear regression validity, semi-supervised efficiency, Gaussian decomposition, and PCA variance quantification—showcasing her signature blend of methodological innovation and practical applicability. Witten's exceptional contributions are recognized through extensive honors: Presidents’ Award, Committee of Presidents of Statistical Societies (COPSS) (2022) Mortimer Spiegelman Award, American Public Health Association (2019) Simons Investigator Award (2018-2023) Sloan Research Fellowship (2013-2015) NSF CAREER Award (2013-2018) NIH Director’s Early Independence Award (2011-2016) 23 major awards including named lectureships, fellowships, and editorial leadership As a dedicated mentor, she has guided students like Olivia McGough (NSF GRFP winner), Dwight (Zichun) Xu (ASA Nonparametrics Student Paper Award winner), Yiqun Chen (Hopkins Biostat faculty), and Anna Neufeld (Williams College faculty). Her research is sustained by major grants from NIH, NSF, and Simons Foundation. Witten co-authored the seminal textbook "Introduction to Statistical Learning" and currently serves as Joint Editor of the Journal of the Royal Statistical Society, Series B (2023-2025), shaping the field through both scholarship and community leadership.