Find Academic Supervisors

Michael MahoneyView profile

Adjunct Professor

• Statistical Computing
• Artificial Intelligence/Machine Learning
• High Dimensional Data Analysis
• +3 more

Michael Mahoney is an Adjunct Professor in the Department of Statistics at University of California, Berkeley . He is also affiliated with the International Computer Science Institute (ICSI) as Vice President and Director of the Big Data Group, and the Lawrence Berkeley National Laboratory (LBNL) as Group Lead of the Machine Learning and Analytics Group. His research focuses on Randomized Numerical Linear Algebra (RandNLA) , Machine Learning , and Scientific Computing , with applications in genetics, climate science, social networks, and physics-informed models. Mahoney leads initiatives such as the Foundations of Data Analysis (FODA) Institute and develops tools like RandBLAS/RandLAPACK for scalable linear algebra. Research Interests Mahoney’s work bridges theoretical and applied domains. Key areas include: RandNLA : Leveraging randomness for efficient matrix computations, with implementations in distributed systems. Deep Learning Theory : Exploring implicit regularization, heavy-tailed dynamics, and self-organization in neural networks. Scientific ML : Combining domain-driven models (e.g., PDEs) with data-driven approaches for physical systems like fluid dynamics and seismology. Teaching & Mentorship He teaches advanced courses on Linear Algebra for Data Science and Randomized Linear Algebra , emphasizing foundational methods relevant to modern ML. Mahoney has advised numerous PhD and Master’s students across disciplines, fostering innovation in scalable algorithms and their applications. Grants & Collaborations Mahoney’s funding includes NSF, DOE, and DARPA grants for projects like Scientific Foundation Models and Heavy-Tailed ML Dynamics . His collaborations span academia (e.g., MIT, Stanford) and industry (Amazon, NVIDIA), focusing on computational efficiency and real-world impact.

• Bayesian statistics
• Spatio-temporal modeling
• Environmental science
• +4 more

Edward Cripps is an Associate Professor in the School of Physics, Maths and Computing at The University of Western Australia, specializing in Mathematics and Statistics. He holds degrees including a BEc from UWA and a PhD in Statistics from UNSW. His research focuses on Bayesian longitudinal analysis, spatio-temporal models, and integrating physical models with probabilistic approaches for environmental, meteorological, and oceanographic applications. He leads major grants including the ARC Industrial Transformation Research Hub for Transforming Energy Infrastructure (2021-2025) and the DARE Training Centre (2021-2025). Collaborations include industry partners like INPEX, Shell, Woodside, and governmental bodies such as the Bureau of Meteorology. He teaches undergraduate courses in probability and applied statistics. Grants & Awards: ARC Hub ($10M) as Chief Investigator/Data Science Leader (2021-2025) MinEx CRC 2022-2023 publication prize (2023) Research Interests: His work addresses model-data mismatch in complex systems, leveraging high-quality data for decision-making in resource management and engineering. Recent projects include geophysical feature discovery, spectral estimation bias correction, and offshore wind turbine structural analysis.

Visakan KadirkamanathanView profile

Professor

• System Identification
• Signal and Information Processing
• Fault Detection and Diagnosis
• +5 more

Professor Visakan Kadirkamanathan is a faculty member in the Department of Automatic Control & Systems Engineering at the University of Sheffield, holding the rank of Professor of Signal and Information Processing. He is the Director of the Rolls-Royce University Technology Centre in Control and Systems Engineering. Born in Jaffna, Sri Lanka, he obtained a Class I Degree in Electrical and Information Sciences from the University of Cambridge (1987) and a Ph.D. in Information Engineering (1990). His career includes roles as Head of Department (2009–2014) and leadership in research excellence frameworks. Research interests span System Identification, Signal Processing, Fault Detection, and applications in Aerospace, Manufacturing, and Healthcare. Education: Ph.D. in Information Engineering (Cambridge, 1990); BEng (Class I, Cambridge, 1987) Research: Focus on spatio-temporal systems, neural field models, and healthcare applications. Notable work includes bone adaptation modeling and biomedical signal processing. Awards: 2012 PNAS Cozzarelli Prize for research on bone remodeling and conflict dynamics modeling. Labs/Teams: Leads the Rolls-Royce UTC and collaborates with the Centre for Signal Processing and Complex Systems. Publications span over 30 years, with recent contributions in neural networks, aerospace systems, and biomedical engineering. He has served as Editor-in-Chief of the International Journal of Systems Science and Conference Chair for major conferences.

• Statistical Methodology
• Neuroscience
• Healthcare Analytics
• +3 more

Dr. Nicolò Margaritella is a Lecturer in Statistics at the School of Mathematics and Statistics, University of St Andrews. His research focuses on developing statistical methodologies for neuroscience and healthcare applications, emphasizing Bayesian approaches for complex spatio-temporal data and large-scale inference problems. He holds an Associate Fellowship of the Higher Education Academy (AFHEA, 2018). Research Interests: Dr. Margaritella specializes in statistical methods for neuroscientific data, including functional principal component analysis, Bayesian FDR estimation, and brain network construction. His work addresses challenges in multiple sclerosis rehabilitation, Alzheimer's disease biomarkers, and infectious disease diagnostics. He has developed the APFr R package for robust multiple testing via Bayes FDR estimation, available on CRAN. Key Publications: Over 11 peer-reviewed articles (2012–2024), including high-impact studies in Scientific Reports , Statistics in Medicine , and Neurological Sciences . Awards: AFHEA (2018). Advising: Supervising PhD student Hanyu Wang. Grants: Secured funding via two LMS grants (2020–2022) for Bayesian methodology and time series analysis research. His research contributes to UN SDG 3 (Good Health & Wellbeing) through innovations in diagnostic tools and treatment efficacy assessments in neurological and infectious diseases.

• Statistical Modelling
• Epidemiology
• Bayesian Inference
• +4 more

Dr Ben Swallow is a Lecturer in Statistics at the University of St Andrews, affiliated with the School of Mathematics and Statistics. His research focuses on statistical methodology applied to epidemiological and ecological problems, with a particular emphasis on Bayesian inference, agent-based models, and public health surveillance. He has contributed to high-impact studies on pandemic response, vaccine efficacy analysis, and wildlife population dynamics. Dr Swallow has supervised PhD students Xiahui Li and Rebecca Supple. His work bridges theoretical statistics with practical applications, including modeling virus transmission dynamics, analyzing ecological data from citizen science projects, and developing computational tools for epidemiological research. Key contributions include advancements in agent-based model calibration, statistical methods for evaluating vaccine safety, and Bayesian approaches to infectious disease modeling. His research outputs span journals such as Journal of Theoretical Biology , BMC Biology , and Journal of the Royal Statistical Society . He actively participates in academic discussions, including contributing to the 'Discussion Meeting on Analysis of citizen science data'.

• Environmental statistics
• Bayesian statistics
• Spatial statistics
• +3 more

Andrew O. Finley is a Professor at Michigan State University with joint appointments in Forestry and Statistics & Probability. He leads the Geospatial Lab, focusing on environmental statistics, Bayesian modeling, and spatial analysis. His research integrates hierarchical models to enhance ecological and forestry data analysis, with applications in forest inventory, carbon monitoring, and biodiversity assessment. Education includes a PhD from the University of Minnesota (2007), MS in Statistics (2007) and Forestry (2003), and a BS from Penn State (2000). He has held NSF, NASA, and USDA grants totaling over $10M, advancing carbon monitoring and statistical methodologies. Research interests span Bayesian statistics, spatial-temporal modeling, and computational tools for large datasets. Notable contributions include the spBayes and spNNGP R packages, widely used for spatial analysis. His work has been recognized with ASA awards and fellowships. Recent projects include assessing western US tree species decline, developing scalable carbon monitoring frameworks, and integrating remote sensing with field data. He advises over 20 graduate students and collaborates globally on ecological and environmental challenges.

Shanshan ZhaoView profile

Adjunct Associate Professor

• Biostatistics
• Environmental Health
• Cancer Research
• +7 more

Dr. Shanshan Zhao is an Adjunct Associate Professor in the Department of Biostatistics at the University of North Carolina at Chapel Hill and a Principal Investigator at the National Institute of Environmental Health Sciences (NIEHS). Her research focuses on developing statistical methods to understand environmental and social influences on health, particularly in cancer epidemiology and risk prediction. She holds a secondary appointment in the NIEHS Epidemiology Branch and leads a group integrating statistical methodology with population-based studies. Her work emphasizes disease risk assessment using survival analysis, longitudinal data, and biomarker evaluation. Key research areas include multivariate failure time data, environmental mixture analysis, and epigenetic biomarkers. She has contributed to studies on breast, prostate, and colorectal cancers, emphasizing spatial-temporal modeling and public health applications. Zhao’s awards include the 2014 ASA David P. Byar Travel Award and recognition for her 2023 NIEHS publication on environmental breast cancer risk factors. Her team develops software tools like mhazard for multivariate survival analysis and STAFT for spatio-temporal modeling. Her lab collaborates across disciplines to advance environmental health sciences, with a focus on translating statistical innovations into actionable insights for clinicians and policymakers.

Kevin NowkaView profile

Academic

• Semiconductor Design
• Computer Architecture
• Memory Systems
• +2 more

Kevin Nowka is Professor of Practice in Electrical and Computer Engineering at Texas A&M University's College of Engineering. His research bridges semiconductor design and agricultural informatics, developing machine learning tools for precision farming and wildfire prediction. Education and industry background include extensive experience in high-frequency processor design and VLSI systems. Previous roles include IBM Research leadership in memory systems and low-power architectures. Research applies deep learning to environmental challenges, notably through UAS-based crop monitoring frameworks and neural network optimization for embedded agricultural systems. Recent work focuses on cotton yield forecasting using Bayesian networks and LSTM models. Publications show convergence of semiconductor expertise and agri-informatics, with innovations in model compression for edge computing in field applications. Key themes include phenotyping automation and privacy-preserving data analytics. Teaches courses on computer architecture and embedded systems. Supervises student projects on AI applications in sustainable agriculture.

Rajarshi GuhaniyogiView profile

Associate Professor

• Bayesian Statistics
• Machine Learning
• Big Data Analytics
• +9 more

Rajarshi Guhaniyogi is an Associate Professor in the Department of Statistics at Texas A&M University, College of Arts & Sciences. His research focuses on Bayesian methodology for complex biomedical and machine learning applications, including scalable Bayesian methods, spatial/spatio-temporal statistics, and tensor analysis. He has been recognized with prestigious awards such as the 2023 Early Investigator Award from ASA ENVR and the 2023 ECASDS Award from IISA. Key collaborations include work with neuroscientists on multi-modal neuroimaging data and environmental scientists on remote sensing data. His research is supported by grants from NIH, NSF, Department of Energy, and Office of Naval Research. Rajarshi will transition to a Full Professor role in August 2025. Recent work emphasizes distributed Bayesian inference for large datasets, Bayesian tensor regression, and robust computation strategies for high-dimensional data. He has contributed to journals like Biostatistics , Technometrics , and Journal of Machine Learning Research , and serves on editorial boards for Journal of Machine Learning Research and Journal of Computational and Graphical Statistics . His grants include an NIH R01 grant (1 percentile score) for Bayesian multi-object data modeling and a DOE grant for spatial modeling of categorical data. He actively organizes conferences like the NSF-sponsored CBMS conference on causal graphical models.

Toryn SchaferView profile

Assistant Professor

• Spatio-temporal statistics
• Reinforcement learning
• Bayesian statistics
• +5 more

Toryn Schafer is an Assistant Professor in the Department of Statistics at Texas A&M University, holding the 2024 ConocoPhillips Data Science Faculty Fellowship. Previously, he was a postdoctoral associate at Cornell University's Department of Statistics and Data Science, contributing to the NSF-funded PRISM Institute for Trans-domain Systemic Risk. His academic journey includes a PhD in Statistics (2020) from the University of Missouri, an MA in Statistics (2018), and a BSc in Statistics & Wildlife Biology (2014) from Colorado State University. His research interests focus on spatio-temporal statistics, reinforcement learning, Bayesian methods, and machine learning, applied to ecological and environmental systems. He emphasizes interdisciplinary approaches to address challenges in energy, sports analytics, and biodiversity conservation. His recent work explores advanced statistical methods for trend analysis, changepoint detection in time series, and the integration of community science data for ecological modeling. Notable contributions include Bayesian inverse reinforcement learning frameworks for animal behavior analysis and studies on renewable energy impacts on electricity markets. Education: PhD in Statistics, University of Missouri (2020) MA in Statistics, University of Missouri (2018) BSc in Statistics & Wildlife Biology, Colorado State University (2014) Research Themes: His publications reflect a trajectory toward methodological advancements in spatio-temporal modeling, with applications ranging from animal movement patterns to energy grid resilience. Recent articles highlight critical risk indicators for power systems and biodiversity status metrics inspired by financial portfolio theory. Grants & Fellowships: 2024 ConocoPhillips Data Science Faculty Fellowship (Texas A&M University). Labs/Teams: While specific lab affiliations are not detailed, his work intersects with interdisciplinary teams focused on ecological data science and systemic risk analysis.

Kostas KalogeropoulosView profile

Associate Professor

• Bayesian Inference
• Stochastic Differential Equations
• Markov Chain Monte Carlo
• +6 more

Kostas Kalogeropoulos is an Associate Professor and MSc Statistics Programme Director in the Department of Statistics at the London School of Economics and Political Science (LSE). He previously served as a post-doctoral researcher at the University of Cambridge's Signal Processing Laboratory and holds a PhD from the Athens University of Economics and Business. His research focuses on Bayesian inference methodologies applied to stochastic differential equations, with applications in financial econometrics, biomedical modeling (e.g., epidemic dynamics), and growth curve analysis. Dr. Kalogeropoulos teaches advanced courses including ST451: Bayesian Machine Learning and ST308: Bayesian Inference at LSE, as well as the summer school course ME315: Machine Learning in Practice. He is actively involved in academic administration as Programme Director of LSE’s MSc in Statistics and organizes the Theory of Machine Learning Reading Group. His professional affiliations include the Data Science Group and Social Statistics Group within the LSE Department of Statistics, as well as leadership roles in the Greek Stochastics Team. His research outputs span computational statistics and applied Bayesian methods, with notable contributions to spatio-temporal epidemic modeling, stochastic volatility analysis, and dynamic term structure modeling. He has collaborated with international institutions on projects addressing public health challenges and financial econometric applications.

Eike MuellerView profile

Associate Professor

• Numerical Analysis
• Parallel Computing
• Partial Differential Equations
• +2 more

Dr. Eike Mueller is a Reader (Associate Professor) in the Department of Mathematical Sciences at the University of Bath. His research focuses on developing fast numerical algorithms for solving physical problems across scales, from atmospheric models to subatomic particles. As part of the Numerical Analysis group, he specializes in parallel computing implementations using frameworks like DUNE and Firedrake/PyOP2. His work is characterized by close collaboration with the Met Office on weather and climate forecasting models. Research interests center on numerical techniques for complex systems, emphasizing parallel computing architectures including GPU clusters. Key areas include massively parallel solvers for PDEs, multilevel Monte Carlo methods for atmospheric dispersion, and performance-portable frameworks for physics simulations. Recent work explores machine learning integration with traditional numerical methods for enhanced computational efficiency. Publications demonstrate consistent focus on accelerating scientific computation through novel algorithms. Recent articles emphasize the application of multigrid methods to climate modeling, neural networks in numerical integration, and Bayesian inference techniques. A significant portion of work targets performance optimization on modern hardware architectures including GPU acceleration. Research leadership includes principal investigator roles for major EPSRC projects: 'MGHyPE: An ExaHyPE version with a multigrid solver' and 'IAA – Accelerating climate- and weather-forecasts with faster multigrid solvers'. Collaboration with the Met Office has resulted in operational improvements to weather prediction models through bespoke solver development.

• Statistics
• Biostatistics
• Spatial Epidemiology
• +5 more

Theresa Smith is a Senior Lecturer in the Department of Mathematical Sciences at the University of Bath, affiliated with centers including the EPSRC Centre for Doctoral Training in Statistical Applied Mathematics (SAMBa), the Centre for Mathematics and Algorithms for Data (MAD), and the Centre for Therapeutic Innovation. Her research focuses on statistical methods for spatial and longitudinal data, with applications in health and social sciences, particularly clinical decision support tools. She holds a PhD in Statistics from the University of Washington (2014) and previously served as a Senior Research Associate at Lancaster University (2014–2016). Her research interests include spatial epidemiology, Bayesian inference, and biostatistical modeling. She leads projects such as the TULiPS study on psoriasis burden and the AI4CI Hub for collective intelligence research. Notable collaborations involve developing AI-driven solutions for public health challenges and advancing wastewater-based epidemiology for disease monitoring. Dr. Smith has secured grants from the NIHR, EPSRC, and the Royal Society, including a Short Industry Fellowship for predictive analytics in electronic health records. She advises students like N. Khaleel, whose thesis she supervised. Her work contributes to Sustainable Development Goals related to health and well-being. She is also part of interdisciplinary teams addressing environmental health risks and urban transport policy impacts.

• Data Science
• Computational Statistics
• Bayesian Models
• +5 more

Antonietta Mira is a Full Professor of Statistics at the University of Italian Switzerland (USI), where she also serves as the founder and director of the Data Science Lab. She holds a part-time professorship at Università dell'Insubria and has held visiting roles at institutions such as the University of Cambridge and Université Paris-Dauphine. Her academic leadership includes a Vice-Dean role in the Faculty of Economics (2013-2015). She earned a PhD in Computational Statistics from the University of Minnesota (1998), a Master's in Statistics (1996), and a Doctorate in Methodological Statistics from the University of Trento (1995). Her research focuses on Bayesian statistical models, computational statistics, and interdisciplinary applications in healthcare, finance, and social sciences. Mira is a Fellow of the International Society for Bayesian Analysis (ISBA) and the Istituto Lombardo Accademia di Scienze e Lettere. Her work has been recognized with awards for both research and teaching excellence. She leads Swiss National Science Foundation-funded projects and serves on editorial boards of journals like Bayesian Analysis and Statistica Sinica . Her publications span topics such as approximate Bayesian computation (ABC), spatio-temporal modeling of health events, and data science applications in public policy. Mira also engages in public outreach, including scientific exhibitions like Numbed by Numbers! and lectures on data-driven societal issues.

Mihai AnitescuView profile

Professor

• Numerical Optimization
• Uncertainty Quantification
• Numerical Analysis
• +12 more

Mihai Anitescu is a Senior Computational Mathematician in the Laboratory for Advanced Numerical Software (LANS) within the Mathematics and Computer Science Division at Argonne National Laboratory, a position he has held since 2002. He is also a part-time Professor in the Department of Statistics at the University of Chicago since 2009 and an adjunct Associate Professor in the Mathematics Department at the University of Pittsburgh. Additionally, he is a Senior Fellow of the Computation Institute, a joint Argonne-University of Chicago initiative. He leads the MACSER (MultiTimescale Control of Electric Power Systems) project and previously led the M2ACS project. Ph.D., Applied Mathematical and Computational Sciences, University of Iowa, 1997 Electrical Engineer, Polytechnic University of Bucharest, Romania, 1992 Dr. Anitescu’s research focuses on numerical optimization, uncertainty quantification, and numerical analysis, with applications spanning nuclear engineering, electric power grids, chemical engineering, materials science, biology, mechanical engineering, and robotics. His work develops scalable computational methods for complex systems, particularly leveraging high-performance computing. He has made significant contributions to optimization under uncertainty, stochastic programming, Gaussian process modeling, and simulation of multibody dynamics with contact and friction using differential variational inequalities. His recent publications (2020–2023) highlight a strong and consistent trend in applying advanced mathematical and computational techniques to critical energy infrastructure, particularly the electric power grid. Key themes include stochastic optimization for optimal power flow under uncertainty, risk assessment through extreme event simulation, frequency prediction and estimation using spatiotemporal and Bayesian methods, and the simulation of cascading failures. His work bridges core mathematical advances in optimization, sensitivity analysis, and scalable Gaussian process computation with high-impact applications in grid stability, reliability, and control. Dr. Anitescu is a senior editor of Optimization Methods and Software and a member of the editorial boards of Mathematical Programming and the SIAM Journal on Optimization . He has previously served on the editorial boards of the SIAM Journal on Scientific Computing and the SIAM/ASA Journal on Uncertainty Quantification . He is a dedicated mentor, having advised numerous postdoctoral fellows, Ph.D. students, and M.S. students at Argonne, the University of Chicago, and the University of Pittsburgh. His advisees have gone on to successful careers in national laboratories, academia (e.g., UC Santa Barbara, Purdue, University of Wisconsin), and industry (e.g., Amazon, Citibank, Morgan Stanley, IBM). He has secured and led significant research grants through projects like MACSER and M2ACS, which focus on the mathematical challenges of managing complex, uncertain energy systems. His work is highly collaborative, involving partnerships across institutions and disciplines. Dr. Anitescu leads the MACSER project, a major research initiative focused on developing mathematical and computational tools for the multi-timescale control of electric power systems. This work is central to ensuring the stability and reliability of modern power grids, especially as they integrate increasing amounts of renewable energy.