Sparse Modeling Professors and Supervisors in Canada

George Labahnمشاهده پروفایل

استاد

University of WaterlooCanada

George Labahn is Professor and Director of the Symbolic Computation Group at the University of Waterloo's David R. Cheriton School of Computer Science. His research spans computer algebra, computational finance, and pen-based mathematical interfaces. Key contributions include fundamental algorithms for matrix normal forms (Hermite/Smith forms), symbolic-numeric polynomial computation, and development of the MathBrush system for handwritten mathematics recognition. Research focuses on efficient algorithms for polynomial matrix arithmetic, rational approximation, and solving differential equations with elliptic coefficients. Computational finance work develops numerical methods for option pricing under jump diffusion models. Current projects include fast Hermite form computation and rank-sensitive matrix algorithms. Serves as associate editor for Journal of Symbolic Computation (JSC) and previously for ACM Transactions on Mathematical Software (TOMS). Authored core Maple programming guides and implemented key packages for symbolic integration, differential equations, and graphics in Maple.

پروفایل رسمی دانشگاه

Sirisha Rambhatlaمشاهده پروفایل

استادیار

University of WaterlooCanada

Sirisha Rambhatla is an Assistant Professor at the University of Waterloo, holding appointments in the Management Sciences Department (Faculty of Engineering), Systems Design Engineering, and the David R. Cheriton School of Computer Science (Faculty of Mathematics). She leads the CriticalML lab, focusing on reliable AI for healthcare, aviation, and climate change, leveraging deep learning and spatiotemporal analysis. Her work bridges theory and practice, with publications at top venues like NeurIPS, ICLR, and clinical journals. Affiliations include the Waterloo AI Institute and the Waterloo Institute for Sustainable Aeronautics. Education: Ph.D. and M.S. in Electrical Engineering, University of Minnesota (2019, 2012) B.Tech in Electronics and Telecommunication Engineering, College of Engineering Roorkee (2010) Research Interests: Representation Learning, Spatiotemporal Data Analysis, AI for Healthcare, Computer Vision, and provable algorithms. Her work emphasizes interpretable AI and applications in surgery, intelligent automation, and climate modeling. Awards: 2021 Merit Award for Excellence in Postdoctoral Research E. Bruce Lee Memorial Fellowship University Bronze Medalist (2010) Teaching: Courses include Advanced Machine Learning (MSCI 546/MSE 546), Big Data Analytics (MSCI 623), and Special Topics in Management Engineering (MSCI 598/MSE 598). Labs/Teams: Leads the CriticalML lab, focusing on trustworthy AI systems for critical applications.

پروفایل رسمی دانشگاه

Eugene Belilovskyمشاهده پروفایل

دانشیار

University of MontrealCanada

Eugene Belilovsky is an Associate Professor at the University of Montreal's Department of Computer Science and Operational Research and an Assistant Professor at Concordia University's Department of Computer Science and Software Engineering. He is also an Associate Member of Mila – Quebec Institute for Artificial Intelligence. His research focuses on computer vision, deep learning, and their applications in areas like continual learning and few-shot learning at the intersection of vision and natural language processing. Belilovsky's expertise includes distributed systems, federated learning, and optimization. His work addresses challenges in model generalization, spurious correlations, and efficient training strategies. He has advised numerous graduate students, including Charles-Étienne Joseph, Medric B. Djeafea Sonwa, Gwendolyne Legate, and Irene Tenison. His recent publications highlight contributions to federated learning, continual pre-training, and fairness in AI systems. Notable work includes optimizing distributed learning protocols and mitigating forgetting in evolving data streams. Belilovsky's research also explores clinical applications, such as diagnosing hepatic steatosis using ultrasound imaging through deep learning techniques. He collaborates with institutions like Mila and the DIRO department, advancing interdisciplinary projects in AI-driven healthcare, robotics, and language modeling.

پروفایل رسمی دانشگاه

Stephen Kirklandمشاهده پروفایل

استاد

University of ManitobaCanada

Stephen Kirkland is Professor of Mathematics and Associate Dean in the Faculty of Graduate Studies at the University of Manitoba. His research focuses on matrix theory, combinatorial mathematics, and spectral graph theory with applications to Markov chains and network science. Current investigations include Kemeny's constant analysis, quantum state transfer in graphs, and spectral properties of stochastic matrices. His work connects abstract matrix theory with practical applications in epidemiology, network analysis, and quantum computing. Kirkland serves as Editor-in-Chief of Linear and Multilinear Algebra and Senior Editor of Linear Algebra and its Applications. He previously served as President of the International Linear Algebra Society and on scientific advisory boards internationally. He currently supervises graduate students Hermie Monterde, Homer Franz De Vera, Aaron Rossi, and Max Wiebe. His research group investigates mathematical structures underlying complex systems and networks.

پروفایل رسمی دانشگاه

Graham W. Taylorمشاهده پروفایل

استاد

University of GuelphCanada

Graham W. Taylor is a Professor at the University of Guelph , holding the Canada Research Chair in Machine Learning and Canada CIFAR AI Chair . He leads the Machine Learning Research Group and serves as Academic Director at NextAI , with affiliations to the Vector Institute for Artificial Intelligence . PhD in Computer Science from University of Toronto (2009) Postdoc at Courant Institute, New York University (2010-2012) His research focuses on deep learning with emphasis on human-centred AI systems , generative modeling , graph representation learning , and sequential decision making . Applied projects leverage computer vision to address biodiversity loss , leading to datasets like BIOSCAN-5M and BIOSCAN-1M. Recent work explores state space models , transformers , and token clustering in vision transformers. Key scientific contributions recognized through Canada's Top 40 under 40 (2018) and Canada CIFAR AI Chair (2019). His group has received NSERC and OGS funding, with students winning awards like the Michael Smith Foreign Study Supplement and NSF + NSERC grant for biodiversity projects. Former students include PhD graduates like Angus Galloway , Boris Knyazev , and Kristina Kupferschmidt , alongside Master’s students such as Rylee Thompson , Sara El-Shawa , and Mahmoud Gamal . Current advisees include PhD student Kristina Kupferschmidt and Master’s students Tiancheng Gao and Mohamed Mostafa . Co-founder of Deep Biologics Current advisor to 17+ students and postdocs Formerly at Google Brain (2018-2019)

پروفایل رسمی دانشگاه

Renjie Liaoمشاهده پروفایل

استادیار

University of British ColumbiaCanada

Renjie Liao is an Assistant Professor (tenure-track) in the Department of Electrical and Computer Engineering (ECE) at the University of British Columbia (UBC), with an associated appointment in the Department of Computer Science. He is also a Faculty Member at the Vector Institute and a Canada CIFAR AI Chair. Prior to UBC, Dr. Liao was a Visiting Faculty Researcher at Google Brain and held a Senior Research Scientist position at Uber Advanced Technologies Group during his PhD. He earned his B.Eng. (Automation) from Beihang University, M.Phil. (CS) from the Chinese University of Hong Kong, and PhD (CS) from the University of Toronto. His research focuses on probabilistic and geometric deep learning , with key contributions in deep generative models, geometric deep learning, neural algorithmic reasoning, and generalization bounds. Notable areas include 3D point cloud analysis, self-driving systems, and healthcare applications using graph neural networks. His work bridges theoretical foundations (e.g., PAC-Bayes bounds) with practical applications like motion forecasting and medical imaging. Education: B.Eng. in Automation, Beihang University (2011) M.Phil. in Computer Science, CUHK (2015) PhD in Computer Science, UofT (2021) Dr. Liao has received awards such as the RBC Graduate Fellowship and Connaught International Scholarship. His lab (Deep Structured Learning Lab) emphasizes principled mathematical approaches to solving complex problems. He advises students in machine learning, computer vision, and robotics, encouraging applications from those with strong coding/mathematical backgrounds. Labs/Teams: Deep Structured Learning Lab (UBC) Vector Institute Collaboration

پروفایل رسمی دانشگاه

Xiaoxiao Shaun Liمشاهده پروفایل

استادیار

University of British ColumbiaCanada

Xiaoxiao Shaun Li is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of British Columbia (UBC), with an adjunct position at Yale School of Medicine. She holds positions as faculty at the Vector Institute and is a Canada CIFAR AI Chair and Canada Research Chair (Tier II) in Responsible AI. Her research focuses on developing trustworthy and efficient machine learning systems, particularly in federated learning, medical imaging, and agentic AI. Dr. Li earned her Ph.D. from Yale University and completed postdoctoral work at Princeton University. Education: B.S. (Honors), Zhejiang University, China, 2015 Ph.D., Yale University, 2019 Research Interests: Trustworthy AI foundational theories and algorithms Federated learning frameworks for privacy-preserving applications Agentic AI systems with robust decision-making Medical imaging analysis and fairness benchmarking Interpretable neuroimaging models for brain disorder prediction Grants & Awards: Canada Foundation for Innovation Grant (PI, 2023) UBC Green Lab Fund (PI, 2023) Canada Research Chair Tier II (2022–2027) Labs & Teams: Dr. Li leads the Trusted and Efficient AI (TEA) Lab at UBC, focusing on next-generation AI systems. The lab collaborates with industry partners like Vector Institute and academic institutions globally to bridge research and clinical applications.

پروفایل رسمی دانشگاه

Peter Kimمشاهده پروفایل

استاد

University of GuelphCanada

Peter Kim is a Professor in the Department of Mathematics and Statistics at the University of Guelph, specializing in biostatistics, microbiome research, and computational geometry. His work bridges statistical theory, clinical applications, and topological analysis of complex datasets. University: University of Guelph Department: Mathematics and Statistics Email: pkim@uoguelph.ca Research Focus: Peter Kim's research integrates topological data analysis , machine learning , and microbiome studies to address clinical and biological questions, particularly in recurrent Clostridioides difficile infections and precision medicine. He develops geometric statistical models to analyze microbial dynamics and therapeutic outcomes. Recent Trends: His publications emphasize nonparametric regression on symmetric spaces, microbiome engraftment , and clinical efficacy of FMT . Key methodologies include Fréchet analysis, persistent homology, and survival modeling applied to microbial ecosystems and medical imaging.

پروفایل رسمی دانشگاه

Paul Marriottمشاهده پروفایل

استاد

University of WaterlooCanada

Paul Marriott is a Professor in the Department of Statistics and Actuarial Science at the University of Waterloo. His research focuses on integrating geometric principles, particularly differential and convex geometry, into statistical methodologies, with a recent emphasis on mixture models and information geometry. He has published extensively across diverse journals such as Biometrika, Annals of Statistics, and Psychological Medicine, bridging theoretical and applied statistics. Education: PhD, University of Warwick (1989) MA, University of Oxford (1984) Research Trends: His work explores geometric frameworks for statistical inference, mixture model parameterization, and robustness analysis. Recent publications highlight causal modeling, neural spike train analysis, and high-dimensional data applications. Contact: Office: Mathematics & Computer Building (M3) 4204, Phone: 519-888-4911 x35545, Email: pmarriot@math.uwaterloo.ca

پروفایل رسمی دانشگاه

Karen Gundersonمشاهده پروفایل

دانشیار

University of ManitobaCanada

Graph theory
Combinatorics
Random graphs
+۱۰ مورد دیگر

Karen Gunderson is an Associate Professor in the Department of Mathematics at the University of Manitoba's Faculty of Science. Her research spans graph theory, combinatorics, random graphs, percolation, hypergraphs, and extremal combinatorics. Research Focus : Graph theory, combinatorics, random graphs, percolation, hypergraphs, extremal combinatorics Academic Role : Associate Professor, Acting Associate Head Graduate Contact : Karen.Gunderson@umanitoba.ca , karen.gunderson@umanitoba.ca Her work includes bootstrap percolation , random geometric graphs , and extremal hypergraph problems , with applications in network modeling and probabilistic combinatorics. Recent publications focus on adversarial burning densities, Erdos-Ko-Rado robustness, and Turán numbers in switching contexts. Academic Leadership : Co-organizer of the University of Manitoba Combinatorics Seminar and key organizer for the 2023 CanaDAM conference and Movement & Symmetry in Graphs retreat.

پروفایل رسمی دانشگاه

Yoshua Bengioمشاهده پروفایل

استاد

McGill UniversityCanada

Yoshua Bengio is a Full Professor at Université de Montréal, Canada CIFAR AI Chair (2018–present), and founder of Mila – Quebec AI Institute. He co-directs the CIFAR Learning in Machines & Brains program and serves as Scientific Director of IVADO. A Fellow of the Royal Society of London and Canada, and Officer of the Order of Canada, Bengio is a pioneer in deep learning and co-recipient of the 2018 A.M. Turing Award. His research spans Deep learning architectures Neural networks Machine learning theory Generative models Optimization algorithms Recent work focuses on generative adversarial networks, neural machine translation, and theoretical foundations of deep learning. Awards include the Killam Prize (2019), IEEE Neural Networks Pioneer Award (2019), and global recognition as the second-most cited computer scientist (2021).

پروفایل رسمی دانشگاه

Jean Mahseredjianمشاهده پروفایل

استاد

Polytechnic School of MontrealCanada

Jean Mahseredjian is a Full Professor in the Department of Electrical Engineering at Polytechnique Montréal. He holds the NSERC/Hydro-Québec/RTE/EDF/OPAL-RT Industrial Research Chair in Multiscale Time Simulation of Transients in Large-Scale Electrical Networks and is a member of the Institute for Data Valorization (IVADO). His research bridges electrical engineering, numerical methods, and renewable energy integration. Research interests include: Advanced numerical simulation of power system transients Modeling and validation of wind farms and HVDC systems Electromagnetic compatibility and circuit theory Real-time simulation and parallel computing for large-scale grids His recent publications (2025-2026) demonstrate strong emphases on: EMTP simulation advancements for circuit breakers, cables, and converters Renewable integration challenges (wind/PV parks and battery systems) High-performance computing methods for power system analysis Awards and honors: IEEE Fellow (2013) for contributions to power system transients simulation Supervision and collaboration: Mentored 68 graduate students (31 PhD, 37 Master's) Leads industry-funded research with Hydro-Québec, RTE, EDF, and OPAL-RT Develops open-source simulation tools (e.g., Julia-based platforms)

پروفایل رسمی دانشگاه

Yves Grosdidierمشاهده پروفایل

مدرس

University of SherbrookeCanada

Dr. Yves Grosdidier is a Lecturer in the Department of Physics at the University of Sherbrooke's Faculty of Science, where he has taught theoretical physics courses since 2002. His academic journey includes doctoral research at Université de Montréal (1995-2000) and a postdoctoral position as Support Astronomer at Instituto de Astrofísica de Canarias (2000-2001). His research focuses on stellar mass-loss phenomena in Wolf-Rayet stars and planetary nebulae, with particular expertise in turbulent outflows, wind inhomogeneities, and dust formation in massive binary systems. Complementing this astrophysical work, he investigates radiative transfer in multifractal cloud structures , analyzing scaling properties across spatial scales from kilometers to meters using satellite data and Monte Carlo simulations. Analysis of his 59 publications (1997-2009) reveals three dominant research threads: (1) High-resolution studies of Wolf-Rayet nebulae like M1-67 using HST and CFHT data, (2) Characterization of wind fluctuations in [WC]-type planetary nebula nuclei through spectroscopic monitoring, and (3) Development of multifractal models for radiative transfer in optically thick clouds. His most influential works establish scaling laws in astrophysical turbulence and provide evidence for episodic dust formation in long-period WR+O binaries. 5,340 publication reads and 301 citations reflect community engagement with his work Extensive collaboration with international teams including NASA, ESO, and Canadian observatories Methodological contributions to structure function analysis and multifractal modeling As a teaching-focused academic, Dr. Grosdidier integrates his research expertise into theoretical physics instruction while maintaining active research collaborations. His work bridges observational astrophysics and theoretical fluid dynamics, with particular attention to scaling phenomena across multiple orders of magnitude.

پروفایل رسمی دانشگاه

Zeinab Abboudمشاهده پروفایل

پژوهشگر

HEC MontréalCanada

Zeinab Abboud is a Senior Academic Member and PhD researcher at Polytechnique Montréal affiliated with Mila (Québec Artificial Intelligence Institute). Her work focuses on Bayesian neural networks, computer vision, and AI applications in healthcare, particularly medical image analysis. PhD in Artificial Intelligence from Polytechnique Montréal Supervised by Hervé Lombaert Her research addresses computational efficiency in medical image analysis through sparse Bayesian networks, combining deterministic and Bayesian parameter representations to reduce training complexity while maintaining predictive accuracy. She has contributed to multi-label classification (ChestMNIST) and segmentation tasks (ISIC, LIDC-IDRI) in healthcare imaging. The publication Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis (2024) demonstrates her work on reducing Bayesian parameter usage by 95% compared to traditional methods, advancing scalable uncertainty estimation in AI models for medical applications.

پروفایل رسمی دانشگاه