Find Academic Supervisors

Jia-Jie ZhuView profile

Researcher

• Machine Learning
• Optimization
• Optimal Transport
• +5 more

Jia-Jie Zhu is a machine learner and applied mathematician currently serving as head of an independent research group at the Weierstrass Institute for Applied Analysis and Stochastics in Berlin, with an upcoming appointment as tenured associate professor at KTH Royal Institute of Technology in Stockholm. Previously, he conducted postdoctoral research in machine learning at the Max Planck Institute for Intelligent Systems in Tübingen, Germany, following doctoral studies in optimization and numerical analysis at the University of Florida. His research focuses on the mathematical foundations of machine learning and optimization, particularly at the intersection of computational algorithms, dynamical systems, and probability theory. Key areas include: Robust probabilistic machine learning algorithms Kernel methods for distribution manipulation Variational methods for optimization over probability distributions Gradient flows and optimal transport theory Wasserstein and Fisher-Rao geometry Applications in generative modeling and causal inference Dr. Zhu's recent work reveals deep connections between partial differential equations, kernel methods, and machine learning, resulting in theoretically grounded algorithms for handling distribution shifts. His publications demonstrate a consistent trajectory from foundational optimization theory to cutting-edge applications in robust learning and generative modeling, with increasing emphasis on the mathematical structures underlying modern ML systems. He has secured significant research funding, including a DFG Project on 'Optimal Transport and Measure Optimization Foundation for Robust and Causal Machine Learning' within the Priority Program 'Theoretical Foundations of Deep Learning' (SPP 2298), and actively organizes academic events such as the Workshop on Optimal Transport from Theory to Applications (OT-DOM) and upcoming sessions at ICSP 2025 and SwissMAP. As an educator, Dr. Zhu teaches nonparametric statistics at Humboldt University of Berlin and serves as area chair for major conferences including AISTATS 2025. He maintains an active research group with opportunities for master's students, PhD candidates, and postdoctoral researchers interested in the mathematical frontiers of machine learning.

• Econometrics
• Nonparametric Methods
• Financial Economics
• +3 more

Joachim Freyberger is a Professor at the University of Bonn , affiliated with the Department of Economics. He is associated with the Institute for Financial Economics & Statistics and the Hausdorff Center for Mathematics, focusing on econometrics and nonparametric methods. Institute for Financial Economics & Statistics Hausdorff Center for Mathematics His research spans econometrics, nonparametric identification, instrumental variables, and financial economics. Key areas include shape restrictions in estimation, interactive fixed effects in panel data, and structural analysis of consumer markets and asset pricing. Recent publications show a focus on nonparametric econometric theory, interactive fixed effects models, and applications to financial panels. Papers address challenges in identification, confidence band construction, and digital market analysis. He teaches advanced courses including Econometrics I and II , Topics in Econometrics and Statistics , and Research Module in Econometrics at Bonn, as well as introductory and graduate econometrics at UW-Madison.

Enno MammenView profile

Professor

• Nonparametric Statistics
• Bootstrap Methods
• Additive Models
• +6 more

Enno Mammen is a Professor of Mathematical Statistics at Heidelberg University, leading the Institute for Applied Mathematics. His career includes roles as Chair for Mathematical Statistics at Heidelberg (2014–present), Chair for Statistics at the University of Mannheim (2003–2014), and various academic positions since 1986. He holds a PhD (1983) and habilitation (1992) from Heidelberg University. Research interests focus on nonparametric statistics, bootstrap methods, additive models, high-dimensional data, and statistical theory. Key contributions include foundational work on the wild bootstrap, penalized nonparametric estimators, and nonparametric diffusion models. He has authored over 150 papers in top journals like the Annals of Statistics and Biometrika. Current research spans Hawkes processes, neural network statistics, and non-Euclidean data analysis. He has supervised 12 PhD students since 2010, with many progressing to academic roles. Awards include the Heinz Maier Leibnitz Prize (1989) and IMS Fellowship (1998). Active in editorial roles for journals like the Annals of Statistics and Bernoulli. Major funding includes leadership of the DFG-funded Research Training Group 'Statistical Modeling of Complex Systems' (2013–2022) and collaborations with Russian institutions on stochastic differential equations.

• Functional Data
• Time Series Data
• Spatial Statistics
• +6 more

Pramita Bagchi is an Assistant Professor in the Department of Biostatistics & Bioinformatics at The George Washington University (GWU), affiliated with the Milken School of Public Health. She holds a Ph.D. in Statistics from the University of Michigan and completed a postdoctoral fellowship at Ruhr Universitat Bochum in Germany. Her research focuses on developing statistical methodologies for analyzing dependent data, particularly in high-dimensional and functional contexts such as time series, spatial data, and functional observations. Education: Ph.D. in Statistics, University of Michigan, Ann Arbor Postdoctoral Research, Department of Mathematics, Ruhr Universitat Bochum Research Interests: Functional Data Analysis Spatiotemporal Modeling High-Dimensional Data Non-Parametric Inference Healthcare Applications Methodological Development for Biomedical Data Publications span statistical theory (e.g., functional time series analysis) and applied health research (e.g., heart transplant biomarkers, acculturation effects in immigrant health). Recent work emphasizes methodological innovations for complex data structures, blending theoretical rigor with real-world applications in cardiology and epidemiology. Grants & Collaborations: NSF Grant: "Empirical Frequency Band Analysis for Functional Time Series" (2022–2025) INOVA Hospital Grant: "Clinical Data Analytics in Cardiac Transplantation" (2020–2023) Teaching includes advanced courses like Mathematical Statistics I (STAT 872), reflecting her expertise in statistical theory and methodology.

Lionel TruquetView profile

Lecturer

• Time Series Analysis
• Statistics for Dependent Data
• Markov Chains
• +3 more

Lionel Truquet is a Lecturer-Researcher in Statistics and Director of Research at ENSAI (École Nationale de la Statistique et de l'Analyse de l'Information). His research focuses on advanced statistical methodologies, including time series analysis, Markov chains, and ecological data modeling. He has contributed to multivariate autoregressive binary models, compact space time series models, and nonstationary count processes. Research Interests: His work emphasizes statistical theory applied to dependent data, with a strong focus on ecological applications. Key areas include ergodic properties of Markov chains, mixing properties of time series, and modeling presence-absence data. His methods address challenges in high-dimensional and nonstationary environments. Publications: Recent work includes influential contributions such as the TJALLING C. KOOPMANS ECONOMETRIC THEORY PRIZE-winning paper on iterations of dependent random maps. His publications span top journals like Bernoulli, the Annals of Applied Probability, and the Journal of Time Series Analysis, reflecting his expertise in both theoretical and applied statistics. Teaching: He teaches advanced courses such as Asymptotic Statistics and Dependence at the M2 level, reflecting his commitment to training future statisticians in cutting-edge methodologies.

• Artificial Intelligence
• Machine Learning
• Data Mining
• +4 more

Dr. Milos Hauskrecht is a Professor of Computer Science at the University of Pittsburgh's School of Computing and Information. He holds a PhD from MIT (1997) and an M.Sc. from Slovak Technical University (1988). His research focuses on AI, machine learning, and data mining, with applications in medicine and finance. He leads projects in real-time clinical monitoring, anomaly detection, and time-series analysis of EHR data. He has advised numerous PhD and MS students, including notable alumni now at Amazon, DeepMind, and Microsoft. Research interests include reasoning under uncertainty, optimization, and AI-driven medical decision support. Current grants include NIH funding for AI in renal therapy and clinical monitoring. He has published widely in top venues like ICML, NeurIPS, and journals such as Artificial Intelligence in Medicine. His work on conditional outlier detection earned the Homer Warner Award (AMIA 2010). He teaches machine learning and advises on interdisciplinary AI projects.

• Machine Learning
• Control Systems
• Robotics
• +3 more

Sebastian Trimpe is a Full Professor and Head of the Institute for Data Science in Mechanical Engineering at RWTH Aachen University, concurrently serving as Co-Executive Director of the RWTH Center for Artificial Intelligence since 2023. Previously, he led a Max Planck Research Group at the Max Planck Institute for Intelligent Systems from 2018 to 2022. His educational background includes: Ph.D. in Dynamic Systems and Control from ETH Zurich (2013) Dipl.-Ing. (M.Sc.) in Electrical Engineering from TU Hamburg (2007) MBA in Technology Management from TU Hamburg (2007) B.Sc. in General Engineering from TU Hamburg (2005) Professor Trimpe's research integrates machine learning with control theory to address safety and efficiency challenges in autonomous systems. His work spans theoretical frameworks for robust decision-making under uncertainty and practical implementations in robotics, with particular emphasis on event-triggered control, distributed systems, and data-efficient learning methodologies. Key contributions include novel approaches to safe reinforcement learning and model predictive control with guaranteed stability. Analysis of his recent publications reveals a pronounced focus on bridging machine learning with control engineering, especially in safety-critical robotics applications. Common themes include distribution-aware learning for medical diagnostics, diffusion-based control approximation, and hardware-in-the-loop validation of theoretical frameworks, demonstrating strong alignment between algorithmic innovation and real-world deployment. His scientific achievements have been recognized with prestigious honors: IFAC World Congress Interactive Paper Prize (2011) Klaus Tschira Award for public understanding of science (2014) Best Paper Award at International Conference on Cyber-Physical Systems (2019) Future Prize by Ewald Marquardt Stiftung (2020) As institutional leader, he directs the Institute for Data Science in Mechanical Engineering and co-leads the RWTH AI Center, overseeing strategic research initiatives and industry collaborations. His academic service includes editorial roles for IEEE Control Systems Society conferences and participation in the Cluster of Excellence 'Internet of Production'. The Institute for Data Science in Mechanical Engineering operates as a multidisciplinary hub where fundamental research in learning-based control meets industrial applications. Current projects focus on drone swarm coordination, deformable object manipulation, and medical diagnostics systems, leveraging both simulation environments and physical testbeds like the Mini Wheelbot platform.

Marc ToussaintView profile

Professor

• Robotics
• Artificial Intelligence
• Machine Learning
• +3 more

Marc Toussaint is Full Professor leading the Learning & Intelligent Systems Lab at TU Berlin's EECS Faculty. His research integrates machine learning, optimization, and AI reasoning to solve fundamental robotics problems like physical reasoning and human-robot interaction. He holds a physics diploma from University of Cologne and PhD from Ruhr-Universität Bochum. Key research themes include: Task-motion planning integration Reinforcement learning for robotics Physical simulation and control Probabilistic inference methods Recent publications focus on efficient kinodynamic planning, belief space planning under uncertainty, and neural policy learning. He develops open-source robotic tools like the 'robotic python package' used in academic courses worldwide. Toussaint collaborates with Amazon Robotics and MIT CSAIL, and has held positions at Max Planck Institute and University of Stuttgart.

Bernd SturmfelsView profile

Professor

• Algebraic Geometry
• Combinatorics
• Commutative Algebra
• +4 more

Bernd Sturmfels is a leading mathematician serving as Director of the Max Planck Institute for Mathematics in the Sciences in Leipzig since 2017. He is also Professor Emeritus of Mathematics, Statistics, and Computer Science at the University of California, Berkeley, and holds honorary professorships at the Technical University of Berlin and the University of Leipzig. His research bridges pure and applied mathematics, with foundational contributions to algebraic geometry, combinatorics, and computational biology. Education: Sturmfels earned dual Ph.D. degrees in 1987 from the University of Washington and Technische Universität Darmstadt, followed by an honorary doctorate from Goethe University Frankfurt in 2015 and additional honorary doctorates from the University of Bern (2023) and the University of Chicago (2024). Research Interests: His work spans algebraic geometry , combinatorics , commutative algebra , algebraic statistics , convex optimization , and computational biology . He explores deep connections between abstract algebraic structures and practical applications in statistics, optimization, and the life sciences. Publications and Trends: With over 300 research articles and 11 books, his recent work (2022–2025) focuses on advanced topics like Grassmannian geometry, tropical implicitization, quantum chemistry applications, and algebraic statistics. His research increasingly integrates computational methods with theoretical insights, addressing problems in machine learning, phylogenetics, and optimization. Awards and Honors: Sturmfels has received numerous prestigious awards, including: George David Birkhoff Prize in Applied Mathematics (2018) SIAM von Neumann Lecturership (2010) Humboldt Senior Research Prize (2007–2008) David and Lucile Packard Fellowship (1992–1997) Fellowships of the AMS and SIAM Membership in the Berlin-Brandenburg Academy of Sciences and Humanities Mentoring and Grants: He has supervised 60 doctoral students and numerous postdocs, with many securing positions at leading institutions. His mentoring philosophy emphasizes diversity and excellence, as highlighted in his Notices of the AMS article. Funding sources include the NSF, DARPA, and the German National Science Foundation (DFG). Labs and Teams: At the Max Planck Institute, he leads the Nonlinear Algebra group, fostering interdisciplinary collaboration between mathematics and the sciences. His team focuses on developing algebraic methods for data analysis, optimization, and theoretical physics.

Vladislav MorozovView profile

Assistant Professor

• Econometrics
• Nonparametric Statistics
• Semiparametric Statistics
• +2 more

Vladislav Morozov is a tenure track Assistant Professor (W1) of Econometrics and Statistics at the Institute for Financial Economics and Statistics within the Department of Economics at the University of Bonn. He holds a PhD in econometrics from Universitat Pompeu Fabra, Barcelona, and maintains an active research program focused on developing practical statistical methods for handling unobserved heterogeneity in economic applications. His research interests encompass Econometrics , Nonparametric Statistics , Semiparametric Statistics , and methods for addressing Unobserved Heterogeneity . Dr. Morozov investigates how unobserved differences between economic agents affect causal inference, with particular attention to heterogeneous treatment effects and parameters that vary across populations. His work demonstrates that even with limited data (such as just two periods of panel data), it's possible to identify average causal effects despite infinitely many unobserved differences between individuals. His recent publications and blog posts reveal a strong focus on practical statistical methods, including applications of the delta method in statsmodels, visualization of statistical convergence concepts, and critical examinations of common econometric practices like fixed effects modeling and hypothesis testing procedures. His work bridges theoretical econometrics with practical implementation for empirical researchers. Dr. Morozov maintains active engagement with the academic community through his lecture notes on econometrics with unobserved heterogeneity, which cover topics from linear models with heterogeneous coefficients to nonparametric approaches. He has recently shifted from LaTeX Beamer to Quarto Reveal.js for creating reproducible, maintainable presentations that integrate code execution directly into slides. He is an active contributor to methodological discussions in econometrics, particularly regarding the challenges posed by unobserved heterogeneity in non-experimental settings, which can lead to significant bias and invalid inference if not properly addressed. His work provides robust methods for handling these pervasive issues in economic research.

Sven KlaaßenView profile

Research Fellow

• Machine Learning
• Causal Inference
• Deep Learning
• +1 more

Dr. Sven Klaaßen serves as a Research Fellow at the University of Hamburg's Hamburg Business School within the Professorship for Statistics with Application in Business Administration, collaborating closely with Prof. Dr. Martin Spindler since 2021. His research focuses on developing advanced statistical methodologies for complex data environments. His academic credentials include: Ph.D. in Statistics from Hamburg Business School (2020) Visiting Scholar at MIT Department of Economics (2022) M.Sc. in Business Mathematics from University of Hamburg (2016) BSc in Business Mathematics from University of Hamburg (2014) Dr. Klaaßen's research program centers on Machine Learning, Causal Inference, Deep Learning, and High-Dimensional Statistics, with particular emphasis on developing robust inference techniques for modern data challenges. His work bridges theoretical statistics with practical applications in business analytics and econometrics, often addressing the complexities of high-dimensional datasets where traditional methods fail. Analysis of his recent publications reveals a clear trajectory toward integrating machine learning with causal inference frameworks, exemplified by his leadership in the DoubleML software ecosystem. His research increasingly tackles multimodal data challenges while maintaining rigorous statistical foundations, with applications spanning economics, operations research, and business decision systems. As an active member of Prof. Spindler's research group, Dr. Klaaßen contributes to collaborative projects developing open-source statistical tools and advancing methodological frontiers in causal machine learning. The team maintains strong industry and academic partnerships focused on translating theoretical innovations into practical analytical solutions.

• Econometrics
• Nonparametric Estimation
• Causal Inference
• +4 more

Christoph Breunig is a Professor in the Department of Economics at the University of Bonn. His work bridges theoretical econometrics with empirical applications, focusing on nonparametric methods, instrumental variable modeling, and causal inference. His research addresses challenges in high-dimensional data, missingness mechanisms, and treatment effect estimation. University: University of Bonn Department: Economics Academic Rank: Professor Email: cbreunig@uni-bonn.de Research Trends: Nonparametric and semiparametric estimation techniques Applications of instrumental variables in causal inference Handling missing data and measurement error High-dimensional statistical models with economic applications Specification testing in complex regression frameworks Connections between microeconomic theory and empirical methods

Göran KauermannView profile

Professor

• Nonparametric Models
• Semi- and nonparametric analysis
• Generalized Linear Models
• +2 more

Prof. Dr. Göran Kauermann is a Full Professor of Statistics at the Ludwig-Maximilians-University Munich , holding the Chair of Applied Statistics in Social Sciences, Economics and Business . His research spans nonparametric models, generalized linear models, and network data analysis, with applications in economics, epidemiology, and data science. Education: Diplom in Economic Mathematics (1991, TU Berlin), PhD in Statistics (1994), Habilitation (Venia Legendi) in Statistics (2000) Kauermann’s research interests focus on penalized regression , network analysis , and statistical modeling in economics, social sciences, and public health. Recent work explores label uncertainty in machine learning , spatio-temporal conflict diffusion , and dynamic network models for economic and social data. Scientific trends in his publications include penalized splines for nonlinear modeling, network flow estimation in social and economic contexts, and label variation analysis in machine learning. His collaborations span climate zone classification , Covid-19 mortality modeling , and smart city parking analytics . Scientific Awards: Bruce Russett Award (2020) for political network research Leadership Roles: He served as Dean of the Faculty of Mathematics, Informatics and Statistics (2019–2021), Speaker of the Elite Master Program in Data Science (2016–2026), and Chair of the German Statistical Society (2005–2013). He also held editorial roles in journals like AStA Advances in Statistical Analysis and Statistical Modelling .

Isabel Valera MartinezView profile

Professor

• Machine Learning
• Artificial Intelligence
• Data Science
• +4 more

Isabel Valera Martínez is a full Professor of Machine Learning at the Department of Computer Science, Saarland University, and an Adjunct Faculty at the Max Planck Institute for Software Systems (MPI-SWS). She holds a PhD in Machine Learning from the University Carlos III of Madrid and has held prestigious fellowships including the Humboldt Postdoctoral Fellowship and the Minerva Fast Track Fellowship from the Max Planck Society. Her research focuses on developing interpretable, robust, and fair machine learning methods, with applications in healthcare, social systems, and consequential decision-making like hiring and loan approvals. Education: PhD in Machine Learning (2014) and MSc in Multimedia and Communications (2012) from University Carlos III of Madrid; Master’s work at Leibniz University Hannover (2009); Telecommunications Engineering from the Technical University of Cartagena (2009). Research Interests: Fairness in AI, Bayesian nonparametric models, robust machine learning, and applications in healthcare and social systems. She co-leads the ELLIS Robust Machine Learning program and the Saarbrücken AI & Machine Learning (SAM) Unit. Key Publications: Contributions to fair classification frameworks, automatic discovery of data types, and modeling psychiatric comorbidity. Notable venues include AAAI, NIPS/NeurIPS, JMLR, and ICML. Awards: Humboldt Fellowship, Minerva Fellowship, Best Paper Honorable Mention at WWW 2017. Labs & Collaborations: Active in the ELLIS Society and MPI-SWS, focusing on interdisciplinary AI applications.

Richard A. DavisView profile

Professor

• Applied Probability
• Time Series Analysis
• Stochastic Processes
• +4 more

Richard A. Davis is a Professor of Statistics at Columbia University and a Hans Fischer Senior Fellow at the Technical University of Munich's Institute for Advanced Study (TUM-IAS). He holds the Howard Levene Professorship in Statistics. His research focuses on applied probability, time series analysis, stochastic processes, and extreme value theory. Davis has contributed to nonlinear time series models, spatial modeling, and financial econometrics. He has held academic positions at Colorado State University and MIT, and has been recognized with awards including the Koopmans Prize, IBM Faculty Award, and fellowships from the Institute of Mathematical Statistics and American Statistical Association. His education includes a B.A. and Ph.D. in Mathematics from the University of California, San Diego. He co-authored influential textbooks like Time Series: Theory and Methods and has advised numerous papers on topics ranging from count time series to spatial extremes. Current research explores machine learning applications in time series and environmental risk modeling through collaborations like the STARMAP program.