Find Academic Supervisors

Grzegorz MzykView profile

Professor

• System identification
• Adaptive control
• Statistical learning
• +5 more

Grzegorz Mzyk is a Professor at Wrocław University of Science and Technology, specializing in control systems and data analysis. His research focuses on developing advanced methodologies for nonlinear system identification and statistical learning, with particular expertise in Hammerstein-Wiener systems, kernel methods, and adaptive control techniques. His core research interests span: System identification : Developing nonparametric methods for complex nonlinear systems Adaptive control : Creating robust algorithms for time-varying environments Statistical learning : Applying kernel methods and entropic metrics to data analysis Cyclostationary analysis : Innovating excitation techniques for dimensionality reduction Recent publications demonstrate strong focus on: Advancing identification techniques for Wiener-Hammerstein systems Implementing adversarial training for secure system modeling Developing error detection methods for databases using machine learning Optimizing procurement strategies through demand forecasting These works integrate control theory with contemporary machine learning approaches.

• Analytic Combinatorics
• Enumerative Combinatorics
• Asymptotic Analysis
• +2 more

Stephen Melczer is an Assistant Professor in Combinatorics and Optimization at the Cheriton School of Computer Science, University of Waterloo. His research advances analytic combinatorics, lattice path enumeration, and symbolic computation techniques. Research develops multivariate methods for asymptotic enumeration, including work on generating functions, lattice paths, and tree structures. Recent publications focus on SageMath implementations, AVL tree encodings, and singularity analysis. Publications demonstrate consistent innovation in combinatorial algorithms with applications to information theory and data structures. Work integrates symbolic computation with asymptotic analysis for rigorous combinatorial results.

Sayan BanerjeeView profile

Associate Professor

• Probability Theory
• Stochastic Processes
• Interacting Particle Systems
• +9 more

Sayan Banerjee is an Associate Professor in the Department of Statistics and Operations Research at the University of North Carolina at Chapel Hill, within the College of Arts and Sciences. His research lies at the intersection of probability theory, stochastic processes, and network science, with applications in operations research and statistical physics. Research Interests: His work focuses on interacting particle systems, ergodicity of diffusions, stochastic networks, probabilistic couplings, and dynamic random graphs. He also investigates random walks in random environments, random matrices, and network sampling and ranking algorithms. These areas reflect a deep engagement with both theoretical probability and its real-world applications in complex systems. Recent Publication Trends: His recent articles (2023–2025) reveal a strong focus on the analysis of infinite particle systems (e.g., Atlas models), dynamic network evolution under various delay regimes, convergence properties of machine learning algorithms like Stein Variational Gradient Descent, and structural properties of random graphs. The keywords span probability, operations research, network science, and computational statistics, indicating interdisciplinary impact. Subfields include rank-based diffusions, local weak convergence, load balancing, flocking dynamics, and network centrality. Scientific Awards: NSF CAREER Award (DMS-2141621) Grants and Advising: He is the principal investigator on the NSF CAREER award DMS-2141621 and a co-PI on the NSF RTG grant DMS-2134107, supporting research training in probability and stochastic processes. While no formal list of students is provided, his role as a Ph.D.-granting faculty member in a top statistics department implies active graduate student mentorship. His prior postdoctoral fellowship at the University of Warwick under Prof. Wilfrid Kendall highlights strong international collaboration. Laboratories and Research Teams: Though no named lab is mentioned, his extensive collaborative network—including researchers like A. Budhiraja, S. Bhamidi, P. Dey, and M. Olvera-Cravioto—indicates leadership in a vibrant research group focused on stochastic modeling and network analysis at UNC.

Mikhail BelkinView profile

Professor

• Machine Learning
• Deep Learning
• Feature Learning
• +5 more

Mikhail Belkin is a Professor at the Halicioglu Data Science Institute and the Computer Science and Engineering Department at the University of California San Diego (UCSD), as well as an Amazon Scholar. His research focuses on foundational aspects of machine learning, particularly deep learning and large language models, emphasizing understanding phenomena like feature learning, over-parameterization, and generalization. He serves as editor-in-chief of the SIAM Journal on Mathematics of Data Science (SIMODS) and was elected an ACM Fellow in 2023. Research Interests: Generalization theory in deep learning Optimization dynamics and convergence Feature learning mechanisms in neural networks Kernel methods and their connections to neural networks Double descent phenomenon and model complexity Key Contributions: Belkin's work has advanced understanding of interpolation in over-parameterized models, revealing how zero-training-error models can generalize well despite classical statistical concerns. His analyses of optimization landscapes and loss surfaces have clarified why gradient-based methods succeed in deep learning. He introduced the Average Gradient Outer Product (AGOP) framework to explain feature learning in neural networks, bridging classical kernel methods and modern architectures. Publications: His recent work explores feature learning in neural networks, convolutional architectures, and the theoretical underpinnings of LLMs. Over 15 recent papers are listed, spanning topics like kernel regression, matrix completion, and the mathematical foundations of deep learning. Awards & Grants: ACM Fellow (2023) NSF/Simons Collaboration on Theoretical Foundations of Deep Learning PI in the TILOS AI Institute (NSF-funded) Advising & Teams: Belkin collaborates with interdisciplinary teams at UCSD and institutions like the Broad Institute’s Eric and Wendy Schmidt Center, focusing on AI’s societal implications and scientific applications. His work emphasizes bridging theory and practice, with algorithms like Recursive Feature Machines (RFM) and EigenPro showcasing scalable, interpretable machine learning solutions.

• Financial Mathematics
• Machine Learning
• Data Science

Dr. Huy Chau is a Lecturer in Financial Mathematics and Statistics at the Department of Mathematics, The University of Manchester. He holds a PhD from the University of Padova and Université Paris Diderot, under Professors Wolfgang J. Runggaldier and Peter Tankov. Prior to his current role, he worked as a Post-doctoral researcher at the Alfred Renyi Institute of Mathematics and as a Specially Appointed Assistant Professor at Osaka University's Center for Mathematical Modeling and Data Science. His research focuses on financial mathematics, machine learning, and data science. Key areas include stochastic processes, utility maximization, transaction costs modeling, and algorithmic trading strategies. His work often bridges theoretical advancements with practical applications in quantitative finance and statistical learning. Recent publications emphasize methodological innovations in pricing/hedging frameworks under market uncertainty, stochastic optimization techniques, and the analysis of behavioral investor dynamics in conic market models. Notable contributions address super-replication strategies under transaction costs and inversion-free numerical methods in statistical computing. Dr. Chau is actively involved in supervising PhD students and teaches advanced courses like Martingales with Applications to Finance. He collaborates internationally on projects such as the UoM-IISc Bangalore PhD initiative.

Thomas PowellView profile

Senior Lecturer

• Proof Theory
• Computability Theory
• Program Semantics
• +8 more

Thomas Powell is a Senior Lecturer (equivalent to Associate Professor) in the Department of Computer Science at the University of Bath. He is a member of the Mathematical Foundations of Computation group. His research focuses on proof theory, computability theory, program semantics, and their applications in mathematics and computer science. Powell holds a PhD in Computer Science from Queen Mary University of London (2013), an MA in Mathematics (Part III) from the University of Cambridge (2009), and a BA in Mathematics (2008). His research interests include proof mining, functional analysis, stochastic processes, and computational algebra. He has led projects funded by the Engineering and Physical Sciences Research Council (EPSRC) and the London Mathematical Society, focusing on imperative program extraction from proofs and logic seminars. Key projects include the EPSRC-funded project Imperative Programs from Proofs and organizing the Southern and Midlands Logic Seminar . Powell has advised multiple PhD students, including Morenikeji Neri and Franziskus Wiesnet, and teaches courses on Foundations of Computation and Data Structures and Algorithms at the University of Bath. Publications span theoretical computer science and mathematics, with recent work on stochastic processes, Tauberian theorems, and algorithmic algebra. His research bridges foundational proof theory with practical applications in analysis and optimization.

Ryan MartinView profile

Professor

• Foundations of statistics
• Foundations of probability
• Generalized Bayes and Gibbs posterior distributions
• +5 more

Ryan Martin is a Professor in the Department of Statistics at North Carolina State University (NC State). He holds a Ph.D. in Statistics from Purdue University (2009) and a B.A. in Mathematics from Franklin College (2003). His research focuses on foundational aspects of statistics and probability, including generalized Bayes methods, imprecise probability, and high-dimensional problems. He co-founded Researchers.One, an innovative peer review platform. Education: Ph.D., Statistics, Purdue University, 2009 M.S., Statistics, Indiana University-Purdue University Indianapolis, 2005 B.A., Mathematics, Franklin College, 2003 Research Interests: His work emphasizes foundational statistical theory, with applications in imprecise probability, Bayesian methods, and high-dimensional inference. Notable contributions include inferential models (IMs), possibilistic frameworks, and regularization techniques for anytime valid inference. He actively explores computational methods for statistical efficiency and reliability. Recent Contributions: Recent work includes advancements in e-processes for efficient uncertainty quantification, variational approximations for possibilistic models, and theoretical developments in Bernstein-von Mises theorems. He also investigates Fisher's underworld and reliability in scientific inference. Awards and Honors: D. D. Mason Award (2022) Van Dantzig Seminar Speaker (2021) Sigma Xi nominee (2020) Thank-a-Teacher Award (2018) I. W. Burr Award (2010) Advising and Grants: He has mentored over 50 graduate students and secured multiple NSF grants. Current projects include Bayesian model selection in high-dimensional settings and imprecise-probabilistic inference. Labs/Teams: Co-leads the Researchers.One initiative, promoting open scholarly communication. Active in collaborative networks on imprecise probability and statistical foundations.

• Soil Science
• Agricultural Statistics
• Environmental Science
• +6 more

Henar Urmeneta Martín-Calero is a Professor at the Department of Statistics, Computer Science and Mathematics, Public University of Navarra. She earned her PhD from the same university in 2003 with an Outstanding 'Cum Laude' distinction. Her work bridges soil science and advanced statistical methodologies. Education : PhD in Statistics and Mathematics (2003), Public University of Navarra Research Interests : Her research focuses on soil inorganic carbon dynamics under agricultural practices, irrigation impacts on soil health, and statistical methods for environmental and agricultural data. She also investigates stochastic processes, generalized Pólya urn models, and convergence theorems in Banach spaces. Publication Trends : Her recent work combines environmental science with statistical innovations, including studies on carbon sequestration in Mediterranean soils (2024), numerical integration techniques (2024), and historical sewage sludge effects on calcareous soils (2022). Earlier contributions involve theoretical mathematics, particularly stochastic circuits and convergence rates. Grants and Projects : She participates in projects like 'Balance de carbono inorgánico en suelos mediterráneos' (2023-2026) and 'Investigación y gestión de operaciones para la mejora de servicios de salud' (2016-2020). She has contributed to contracts evaluating soil properties and vineyard carbon management systems. Research Stays and Collaborations : Completed research stays at the University of Regina (2012) and UNED (2003). She collaborates with journals like Acta Applicandae Mathematicae and participates in academic courts for professor nominations.

Laurent BourgoisView profile

Researcher

• Microelectronics
• Systems Engineering
• Computational Biology
• +3 more

Laurent Bourgois is a Researcher at CentraleSupélec's Department of Microelectronics, focusing on interdisciplinary work at the intersection of microelectronics, systems engineering, and computational biology. His research includes advanced parameter estimation techniques for MEMS resonators, genome assembly challenges in Vanilla planifolia, and innovative approaches to sensor characterization and modeling. Key Research Areas: Microelectronics, Systems Engineering, Computational Biology, Signal Processing Recent Work: 2025 publications on genome assembly complexities and MEMS resonator characterization methods Collaborations: Works with researchers like Jérôme Juillard and Filipe Vinci dos Santos across multiple institutions His technical contributions emphasize nonlinear system identification, fast frequency sweep methodologies, and semi-physical modeling approaches. While no specific awards or students are mentioned in the available data, his publication record demonstrates sustained contributions to both engineering and biological sciences domains.

George GrossmanView profile

Associate Professor

• Algebra
• Number Theory
• Numerical Analysis
• +3 more

George Grossman is an Associate Professor in the Department of Mathematics at Central Michigan University. He holds a Ph.D. (1986), M.S. (1982), and B.A. (1980) from the University of Windsor and York University, respectively. His research focuses on Algebra, Number Theory, Numerical Analysis, and Fluid Dynamics, with notable contributions to combinatorial identities, recurrence relations, and Fibonacci sequence applications. Key research interests include approximations of π, Diophantine equations, and fractal constructions using Fibonacci sequences. He has authored over 20 peer-reviewed articles in journals like the Journal of Integer Sequences and Fibonacci Quarterly . Grossman received a Summer Fellowship for Research at Central Michigan University (1993-1994) and chaired a session at the AMAT 2008 conference. He teaches courses in Calculus, Numerical Analysis, and Math History. His work bridges theoretical mathematics with applied numerical methods, emphasizing interdisciplinary approaches to problems in discrete mathematics and geometric analysis. Collaborations include studies on polynomial zeros and fluid dynamics models. Grossman maintains an active research website and contributes to professional organizations like the Fibonacci Association.

Kailai LiView profile

Assistant Professor

• Robotic Perception
• Sensor Fusion
• State Estimation
• +2 more

Kailai Li is a tenure-track Assistant Professor at the University of Groningen's Bernoulli Institute, where he leads the Agile Sensing and Intelligence Group (ASIG). His research develops novel methods for robotic perception, including continuous-time state estimation, sensor fusion, and visual navigation. Recent publications focus on Gaussian process representations for motion estimation and multi-robot collaboration using vision-language models. Dr. Li's lab maintains open-source projects like LiLi-OM (LiDAR-inertial odometry) and SFUISE (UWB-inertial fusion). Collaborations include Linköping University and industry partners. Current projects investigate trustworthy perception for autonomous systems under uncertainty and efficient representations for high-dimensional state estimation.

Anders HanssonView profile

Professor

• Climate Science
• Environmental Policy
• Sustainability
• +4 more

Anders Hansson is a Professor and Head of Unit in the Department of Thematic Studies - Environmental Change (TEMAM) at Linköping University. His research focuses on interdisciplinary studies of Negative Emission Technologies (NETs), particularly BECCS and biochar, addressing climate change mitigation through technical, social, and economic lenses. He leads the Linköping University Negative Emission Technologies (LUNETs) research group, funded by major grants from the Wallenberg Foundation, Swedish Research Council, and others. His work explores the feasibility, governance, and ethical implications of NETs in Sweden, the Nordic region, Tanzania, and globally. Education: PhD from Linköping University, with prior roles including Senior Lecturer (2008), Docent (2013), and Senior Associate Professor (2021). Research Interests: Climate policy, carbon dioxide removal, socio-technical systems, sustainability transitions, and global environmental governance. He critically examines NETs deployment in developing countries and the role of Integrated Assessment Models (IAMs) in climate science. Grants & Projects: Over SEK 50 million in competitive grants, including projects on climate emergency temporalities, solar geoengineering transparency, and BECCS implementation barriers. Notable funders: Marcus and Amalia Wallenberg Foundation, Swedish Energy Agency, Formas. Labs/Teams: Leads CSPR (Climate Science and Policy Research), STRIPE (Socio-technical research of infrastructures), and collaborates with global institutions like the Leibniz Institute. Engages stakeholders through dialogue platforms to integrate societal perspectives into research.

• Pure Mathematics
• Applied Mathematics
• Discrete Combinatorial Mathematics
• +3 more

Dr. Michael Nyblom is a Lecturer in the School of Science at RMIT University, Australia. His research focuses on Pure and Applied Mathematics, with a particular emphasis on Discrete Combinatorial Mathematics, Number Theory, and their applications to Computer Science. He actively engages in individual and collaborative research, including conference presentations and publications, and explores topics such as Diophantine equations, lattice path counting, and series manipulation. Dr. Nyblom is open to supervising Masters and PhD students in relevant research areas. He holds an ORCID identifier (0000-0001-7903-5705) and can be contacted at michael.nyblom@rmit.edu.au. His teaching interests include Discrete and Combinatorial Mathematics applied to Computer Science. Research highlights include contributions to divergent series analysis, self-avoiding walk enumeration, and number sequence theory. His work spans over two decades, with publications in journals such as the Fibonacci Quarterly, Rocky Mountain Journal of Mathematics, and the Australian Mathematical Society Gazette.

• Control Engineering
• System Identification
• Bayesian Estimation
• +5 more

Adrian Wills is an Associate Professor in the School of Engineering (Mechatronics) at the University of Newcastle, Australia. He leads the Mechatronics Engineering program and holds academic appointments since July 2015. His research focuses on Bayesian estimation, system identification, and control engineering, with applications in robotics and mechatronics. Wills has collaborated with institutions globally, including Linköping University, Uppsala University, and the University of British Columbia. He earned his B.E. (Elec.) and Ph.D. from the University of Newcastle in 1999 and 2003, respectively. Teaching expertise includes delivering advanced courses in estimation and optimization within the Mechatronics Engineering program. Administrative roles include program convenor for Mechatronics Engineering. Research highlights include contributions to state-space models, nonlinear system identification, and model predictive control. His work bridges theoretical advancements with practical applications in engineering systems and healthcare. Key collaborations involve Professors Lennart Ljung, Thomas Schön, and Bhushan Gopaluni, among others. His technical contributions span MATLAB toolboxes (e.g., UNIT), FPGA/ASIC implementations for control systems, and interdisciplinary projects in strain measurement using neutron diffraction.

• Process Control
• Real-Time Optimization
• Chemical Engineering
• +3 more

Dominique Bonvin is a Professor at the School of Engineering (STI) of École Polytechnique Fédérale de Lausanne (EPFL), holding a position within the Automatic Control Laboratory (LA). His research focuses on advanced process control, real-time optimization, and model-based systems engineering. Key topics include modifier adaptation for uncertain systems, dynamic optimization of chemical processes, and control strategies for reaction systems and energy systems. He has published extensively in top-tier journals such as Computers & Chemical Engineering and Journal of Process Control , with over 450 scholarly works to date. His work addresses challenges in industrial processes like wastewater treatment plants, gas compressors, and solid-oxide fuel cells, emphasizing robustness against plant-model mismatches. Collaborations span global institutions, with notable contributions to bioprocess modeling and control of energy-harvesting systems such as kite power. Research Themes: Real-Time Optimization (RTO), Model Predictive Control (MPC), Process Automation, and Systems Engineering Key Technologies: Modifier Adaptation, Dynamic Optimization, Port-Hamiltonian Systems, and Extent-Based Reaction Modeling His recent efforts include accelerating optimization algorithms (e.g., gradient-directed modifier adaptation) and integrating transient measurements for improved plant modeling. He has also pioneered the use of vessel extents to simplify reaction system analysis, enabling decoupled state estimation without full kinetic knowledge.