جست‌وجوی استاد و پژوهشگر

Huang Fangمشاهده پروفایل

پژوهشگر

• Optimization
• Learning theory
• Data mining
• +۳ مورد دیگر

Huang Fang is a Research Scientist at Baidu Research's Cognitive Computing Lab, specializing in optimization theory, machine learning, and data mining. With a strong academic background from top institutions, Huang has established themselves as a prolific researcher in the field of machine learning, particularly in federated learning, privacy-preserving algorithms, and optimization methods. Ph.D. in Computer Science, 2021, University of British Columbia M.S. in Statistics and Computer Science, 2017, University of California, Davis B.Sc. in Financial Mathematics, 2015, Central University of Finance and Economics (China) Huang Fang's research spans multiple critical areas in machine learning, with a particular focus on optimization theory and its applications. Their work bridges theoretical foundations with practical implementations, especially in federated learning systems where privacy and efficiency are paramount. The research portfolio demonstrates expertise in developing novel algorithms for large-scale learning problems, with particular emphasis on convergence analysis, sparse optimization, and scalable methods for knowledge representation. Huang has made significant contributions to understanding the theoretical properties of optimization algorithms under various constraints and settings. The publication record reveals a strong trajectory in advancing machine learning methodologies, with recent work focusing on differentiable neuro-symbolic reasoning, efficient Markov logic networks, and improved convergence guarantees for privacy-preserving stochastic optimization. The research shows a consistent pattern of addressing fundamental challenges in distributed and large-scale machine learning, particularly in the areas of federated learning fairness, efficient coordinate descent methods, and matrix completion techniques. Huang Fang has demonstrated exceptional productivity in high-impact venues including NeurIPS, ICML, ICLR, WWW, and other top-tier machine learning conferences. The work consistently combines theoretical rigor with practical applicability, making significant contributions to both the foundational understanding of optimization methods and their implementation in real-world systems.

• Machine Learning
• Economics/Blockchain
• Mathematical Physics
• +۸ مورد دیگر

Franck Gabriel is an Associate Professor at University Claude Bernard Lyon 1 , affiliated with the Institut de Science Financière et d'Assurances (ISFA) . His research bridges Machine Learning , Economics/Blockchain , Mathematical Physics , and Random Matrices , with notable work on neural tangent kernels, DeFi protocols, and asymptotic matrix theory. Research Focus : Machine Learning: Theoretical analysis of neural networks, kernel methods, and generalization bounds. Blockchain Economics: Decentralized finance, staking mechanisms, and smart contract design. Mathematical Physics: Holonomy fields, Yang-Mills theory, and random matrix asymptotics. Recent Publications highlight trends in denoising diffusion models, free probability in matrix theory, and DeFi credit systems. His work often integrates cross-disciplinary approaches, merging deep learning with financial technology and quantum field theory. Scientific Awards : 2025 AI 2000 Most Influential Scholar Award in Theory 2024 AI 2000 Most Influential Scholar Award in Theory 2023 AI 2000 Most Influential Scholar Award in Theory As an organizer of the ISFA Seminar , he fosters interdisciplinary discussions in insurance, economics, and machine learning. His collaborations span institutions like Ecole Polytechnique Fédérale de Lausanne, Courant Institute, and EPFL.

Joseph Cavanaughمشاهده پروفایل

استاد

• Biostatistics
• Epidemiology
• Public Health
• +۳ مورد دیگر

Joseph Cavanaugh is a Professor in the Department of Biostatistics at the University of Iowa, specializing in biostatistical methods and their applications to public health challenges. His work integrates advanced statistical modeling with real-world epidemiological and safety research, particularly focusing on injury prevention and diagnostic delay analysis across diverse populations. His core research areas include: Biostatistics : Developing novel methodologies for model selection and time series analysis. Epidemiology : Investigating disease patterns and risk factors in population-based studies. Injury Prevention : Analyzing road safety for adolescents and older drivers through naturalistic studies. Diagnostic Delays Research : Quantifying missed opportunities in diagnosing infectious diseases like dengue and sepsis. Statistical Modeling : Advancing information criteria and regularization techniques for heterogeneous data. His recent publications (2024-2025) demonstrate a cohesive research trajectory centered on adolescent road safety interventions, diagnostic delay quantification in infectious diseases, and methodological innovations in model selection. He frequently leverages population-based cohort studies and insurance claims data to identify actionable risk factors, with strong emphasis on translating statistical findings into public health policy recommendations for injury prevention and healthcare quality improvement. Scientific Awards: No awards were documented in the provided sources. Advising and Grants: The available information does not specify any graduate students supervised or research funding secured by Professor Cavanaugh. Laboratories and Teams: No details regarding dedicated research laboratories or collaborative teams were mentioned in the source material.

Matúš Maciakمشاهده پروفایل

دانشیار

• nonparametric regression
• change-points
• structural breaks
• +۵ مورد دیگر

Matúš Maciak is an Associate Professor in the Department of Probability and Mathematical Statistics at the Faculty of Mathematics and Physics, Charles University . His research spans nonparametric regression , change-point detection , and statistical modeling in financial and biological contexts . Key research areas: Nonparametric smoothing and robustness Structural break analysis Shape-constrained inference Sparsity and LASSO-based methods Bootstrapping dependent data Recent publications focus on exogenous market changes , longitudinal data modeling , and biological applications like diel movement patterns in fish. Technical reports include contributions to ecological assessment methods and intercalibration processes for water quality. Contact: Email: Matus.Maciak@mff.cuni.cz , maciak@karlin.mff.cuni.cz Office: K151, Sokolovská 83, Prague 8

Ting Kei Pongمشاهده پروفایل

استاد

• Continuous optimization
• Convex relaxations
• First-order methods
• +۳ مورد دیگر

Ting Kei Pong is a Professor in the Department of Applied Mathematics at the Hong Kong Polytechnic University, where he has been employed since August 1, 2014. His research focuses on continuous optimization, with particular expertise in convex relaxations and first-order methods for large-scale optimization problems. Dr. Pong received his Bachelor's degree in 2004 and MPhil degree in 2006 from the Department of Mathematics at the Chinese University of Hong Kong. He completed his PhD in 2011 from the Department of Mathematics at the University of Washington under the supervision of Professor Paul Tseng, with co-advisement from Professors Maryam Fazel and Rekha Thomas after Professor Tseng's disappearance. His postdoctoral training included positions at the University of Waterloo (2011-2013) and the University of British Columbia (2013-2014) as a PIMS postdoctoral fellow. His research interests span Continuous Optimization , with current focus on convex relaxations and first-order methods for large-scale problems. He also investigates constraint qualifications for convex optimization, statistical computation, and robust optimization. His work bridges theoretical foundations with practical applications in areas such as compressed sensing, sensor network localization, and machine learning. Dr. Pong's publication record demonstrates consistent high-impact contributions to optimization theory. His recent work (2022-2025) shows a strong focus on convergence analysis, error bounds for conic optimization problems, and development of efficient algorithms for nonconvex optimization. His research often combines theoretical analysis with practical implementation, as evidenced by the availability of code for many of his publications. He serves as Associate Editor for Mathematics of Operations Research (since 2019) and on the editorial boards of Computational Optimization and Applications, Pacific Journal of Optimization, and Open Journal of Mathematical Optimization. Dr. Pong actively mentors students and postdocs, currently supervising PhD students Yanbo Wang and Hao Zhang, and postdoc Jiefeng Xu. His former students have secured positions at institutions including the University of Texas Arlington, University of Hong Kong, and Sun Yat-Sen University. His advising reflects his research expertise, with students working on topics in nonconvex optimization, compressed sensing, and matrix factorization. He maintains an active research schedule, regularly presenting at major optimization conferences including ICCOPT, ISMP, and SIAM Optimization. His upcoming talks in 2025 demonstrate continued research productivity in error bounds for log-determinant cones and single-loop proximal-conditional gradient methods.

Giuseppe Carlo Calafioreمشاهده پروفایل

استاد

• Convex Optimization
• Control Systems
• Randomized Algorithms
• +۶ مورد دیگر

Giuseppe Carlo Calafiore is a Full Professor at the Department of Electronics and Telecommunications (DET) of the Polytechnic University of Turin , where he has been since 1998. He has held visiting positions at institutions like Stanford University , University of California at Berkeley , and Vietnam National University . His research focuses on convex optimization , control systems , and randomized algorithms , with applications in finance , robotics , and machine learning . Education : Laurea in Electrical Engineering (1993) and Ph.D in Information and System Theory (1997) from Politecnico di Torino. Research Interests : Span large-scale optimization , robust portfolio optimization , and distributed algorithms , with emphasis on sparsity-based methods and data-driven control for autonomous systems. Recent Publications include works on nonlinear model predictive control , financial network robustness , and adaptive gain control in population games. His scientific awards include the IEEE CSS George S. Axelby Outstanding Paper Award (2008) and Fellow of the IEEE (2018) . He has advised students in artificial intelligence and communications engineering programs. His projects include research on smart energy allocation and financial risk modeling .

Vasilis Syrgkanisمشاهده پروفایل

استادیار

• Machine Learning
• Causal Inference
• Econometrics
• +۵ مورد دیگر

Vasilis Syrgkanis is an Assistant Professor at the Department of Management Science and Engineering , Stanford University, with courtesy appointments in Computer Science and Electrical Engineering. He leads the Stanford Causal AI Lab and is an Associated Director of the Stanford Causal Science Center . His research spans machine learning, causal inference, econometrics, online learning, reinforcement learning, game theory/mechanism design, and algorithm design . Education PhD in Computer Science, Cornell University (advised by Eva Tardos) Diploma in EECS, National Technical University of Athens Research Focus Develops methods for causal machine learning , including courses on Applied Causal Inference and Foundations of Causal ML. Works on treatment effect estimation , instrumental variable regression , and robust policy learning under unobserved heterogeneity. Explores intersections of game theory and machine learning , particularly in auction design and strategic exploration. Scientific Contributions Proposes neural causal partial identification and adaptive instrument design frameworks. Develops doubly robust learning and minimax IV regression algorithms with theoretical guarantees. Introduces incentive-aware synthetic control and structure-agnostic causal effect estimation methods. Awards & Recognition 2023 Bodossaki Distinguished Young Scientist Award in Applied Sciences 2022 Amazon Research Award in Machine Learning Algorithms and Theory Best Paper Awards at COLT 2019, EC 2015, NeurIPS 2015, and others PhD Advisees Ravi Sojitra (MS&E, co-advised with Guido Imbens) Hui Lan (ICME) Jikai Jin (ICME) Jiyuan Tan (MS&E, co-advised with Jose Blanchet) Keertana Veeramony Chidambaram (MS&E) Contact Email: vsyrgk@stanford.edu Office: Huang Engineering Center, Room 252, Stanford, CA 94305

Siddiqua Mazharمشاهده پروفایل

استادیار

• Deep Learning
• Signal Processing
• Mathematics of Neural Networks
• +۳ مورد دیگر

Dr. Siddiqua Mazhar serves as Assistant Professor of Mathematics in the Division of Physical and Computational Sciences at the University of Pittsburgh. Her research pioneers mathematical frameworks for understanding deep learning through signal processing principles. Her educational background includes a Ph.D. in Mathematics (2017) from Newcastle University specializing in Computational Group Theory. Prior to her current role, she worked as a Data Engineer at the University of Arizona and held adjunct teaching positions at Mid Michigan Community College and Southern New Hampshire University. Dr. Mazhar's current research develops novel mathematical theories explaining neural network functionality using transform-domain sparse regularization, Radon transforms, and approximation theory. Her work critically examines weight decay regularization, skip connections, low-rank weight matrices, and sparsity mechanisms in high-dimensional problem solving. She possesses extensive technical expertise in ELT processes, Python, SQL (MySQL, AWS Redshift), NoSQL (MongoDB), Power BI, Docker, Jira, Git, and AWS S3, enabling robust data pipeline development and machine learning implementation. Dr. Mazhar teaches foundational mathematics courses including Calculus I-III, Linear Algebra, Abstract Algebra, Statistics and Probability with Python, Differential Equations, Group Theory, and Semigroup Theory.

Jacek Gondzioمشاهده پروفایل

استاد

• Large Scale Optimization
• Interior Point Methods
• Sparse Matrix Methods
• +۳ مورد دیگر

Jacek Gondzio is a Professor in the School of Mathematics at the University of Edinburgh. He received his M.Eng. in Electronics (1983) and PhD in Automatic Control and Robotics (1989) from Warsaw University of Technology. His career includes positions at the Polish Academy of Sciences (1989–1993), University of Geneva (1993–1998), and the University of Edinburgh since 1998, where he progressed from Lecturer to Professor. Research Interests: Gondzio's work spans large-scale optimization techniques, including interior point methods, sparse matrix computations, parallel algorithms, and applications in finance and engineering. Key focus areas include: Development of efficient solvers (HOPDM, OOPS) for linear/quadratic/nonlinear programming Matrix-free methods and preconditioning for massive-scale problems Applications in quantum information, tomography, structural design, and financial planning Publication Trends: His recent articles emphasize scalable algorithms for optimization, including proximal methods for semidefinite programming, interior-point innovations, and applications in medical imaging and transport. Work frequently integrates regularization, decomposition techniques, and structure-exploiting linear algebra. Awards: EUROPT Fellow (2019) for contributions to continuous optimization Grants & Advising: Current projects include EPSRC-funded work on building structure optimization (EP/N019652/1), Google-funded LP solvers, and risk modeling with Standard Life Investments. He has supervised 16+ PhD students on topics ranging from interior point methods to machine learning optimization. Software includes HOPDM, PDCGM, and the parallel solver OOPS. Leadership: Organizes workshops on optimization (e.g., COA, Advances in Preconditioners series) and serves on editorial boards for Mathematical Programming Computation , Computational Optimization and Applications , and other leading journals.

Junnan Heمشاهده پروفایل

استادیار

• Econometrics
• Decision Theory
• Model Sparsity
• +۳ مورد دیگر

Junnan He is an Assistant Professor in the Department of Economics at Sciences Po (temporarily on leave) and will be the Alliance Visiting Professor at Columbia University's Department of Economics starting Fall 2025. He holds a BSc in Mathematical Economics and Mathematics from the Australian National University (ANU), an MA in Economics from Washington University in St. Louis (WUSTL), and a PhD in Economics from WUSTL. His research focuses on econometrics, decision theory, model sparsity, stochastic choice models, and industrial organization. Key research interests include variable selection in economic models, random choice models, Bayesian methods, and the application of econometric techniques to understand decision-making processes. His work has been recognized through prestigious awards such as the WUSTL Dissertation Fellowship (2017), the Best PhD SPEED Presentation at the OxMetrics Conference (2018), and the ANR Young Researcher Grant (2024) for his project on Complex Decision Making. His publications span topics ranging from VC funding gender gaps to market concentration dynamics in renewables and theoretical advancements in utility models. He has contributed to both empirical and theoretical work in econometrics, bridging methodological innovation with applied economic questions. Professional activities include organizing the IO/Metrics Seminar and maintaining an active presence in academic networks. His research agenda emphasizes bridging gaps between econometric theory and real-world applications in decision-making and market structures.

Christian Luceroمشاهده پروفایل

استادیار

• Inverse Problems
• Uncertainty Quantification
• Machine Learning
• +۲ مورد دیگر

Christian Lucero is a Collegiate Assistant Professor in the Department of Statistics at Virginia Tech's College of Science. He holds a Ph.D. in Mathematical and Computer Sciences from the Colorado School of Mines (2013) with a focus on Bayes Risk A-optimal Experimental Design for inverse problems. His research interests include inverse problems, uncertainty quantification, machine learning, and statistical applications in scientific fields. He is actively involved in undergraduate advising and departmental service, including roles on the Undergraduate Program Committee and Diversity Committee. Education: Ph.D. 2013: Colorado School of Mines (Dissertation: Bayes Risk A-optimal Experimental Design) M.S. 2007: New Mexico Tech (Thesis: Seismic Moment Rate Function Inversions) B.S. Mathematics & Physics: New Mexico Tech (2002-2005) Teaching: CMDA/STAT/CS 3654, STAT 3615/3616, STAT 5615 Service: Member of ASA and SIAM His publications focus on inverse problem methodologies, numerical optimization for ill-posed systems, and geophysical imaging applications. Recent work emphasizes statistical approaches to experimental design in regularization frameworks.

Olalekan Babaniyiمشاهده پروفایل

استادیار

• Inverse Problems
• Biomechanical Imaging
• Computational Mechanics
• +۳ مورد دیگر

Olalekan Babaniyi is an Assistant Professor in the School of Mathematics and Statistics at the Rochester Institute of Technology (RIT), within the College of Science. His research focuses on inverse problems with applications in biomechanical imaging, computational mechanics, and PDE-constrained optimization. He develops mathematical techniques to improve medical imaging and environmental modeling, including real-time imaging of soft tissue mechanical properties and ice flow prediction. He teaches courses such as Probability and Statistics, Boundary Value Problems, and Partial Differential Equations. His work has been highlighted in media for innovative applications in noninvasive disease diagnosis and climate science. Babaniyi runs the Inverse Problems Seminar at RIT (InvPrS) and has published extensively in journals like The Cryosphere, Journal of Nonlinear and Variational Analysis, and Physics in Medicine & Biology. His research emphasizes uncertainty quantification, image denoising in biomedical contexts, and solving inverse problems in viscoelasticity and geophysics. While no personal awards are listed, his contributions have supported student achievements, such as Quinn Kolt’s Goldwater Scholarship in 2021.

Mokhtar Z. Alayaمشاهده پروفایل

استادیار

• Statistical Machine Learning
• Optimal Transport
• High-dimensional Statistics
• +۵ مورد دیگر

Mokhtar Z. Alaya is an Assistant Professor of Statistics and Machine Learning at the Computer Science Department of Université de Technologie de Compiègne (UTC) , where he is affiliated with the LMAC Laboratory . He holds a PhD in Statistical Machine Learning from Université Pierre et Marie Curie (2016) and has conducted postdoctoral research at institutions including Université de Rouen and Université Paris Nanterre. Education: PhD in Statistical Machine Learning, Université Pierre et Marie Curie (2016) Master’s in Statistics and Probabilities, Université Pierre et Marie Curie (2011–2012) Magisterium of Mathematics, University of Gabes, Tunisia (2010) Research Interests: His work focuses on statistical machine learning , including optimal transport for ML applications, high-dimensional statistics, matrix completion, and deep learning. Key projects include interdisciplinary collaborations in mechanics (AI4Meca) and chemistry (AI4Chem), leveraging deep learning for anomaly detection and materials science. Teaching: Courses include Machine Learning , Linear Algebra , and Probability at UTC and international partners like UTSEUS (China). He emphasizes bridging theory and practical coding in Python. Advising & Labs: Supervises PhD students in topics like robust anomaly detection and Frechét regression. Collaborates extensively with the LMAC Lab and cross-disciplinary teams on projects such as generative deep learning for materials engineering.

Stephan Smeekesمشاهده پروفایل

استاد

• Econometrics
• Data Science
• Time Series Analysis
• +۷ مورد دیگر

Stephan Smeekes is a Professor of Econometrics at the Department of Quantitative Economics, School of Business and Economics, Maastricht University. His research focuses on statistical analysis of time series data, blending econometrics, statistics, and data science. Specializing in modeling complex dynamic systems with multiple time series, he emphasizes uncertainty quantification using bootstrap techniques, applied to macroeconomics, finance, climate, environmental, and medical domains. He led significant projects including the NWO Veni project on Bootstrap Methods for Time-Varying Processes and NWO Vidi project on Inference for High-Dimensional Econometric Time Series. As a former member of the Dutch Young Academy (De Jonge Akademie), he contributes to interdisciplinary research and innovation. His teaching spans statistics, econometrics, and computational data science at both undergraduate and graduate levels. Smeekes develops open-source software like the bootUR R package for bootstrap unit root tests, desla for high-dimensional inference, and PAGFL for latent group structure estimation. His work bridges academic insight with real-world impact through collaborations across disciplines.

• Machine Learning
• Operations Research
• Optimization
• +۳ مورد دیگر

Silvia Villa is an Associate Professor in the Department of Mathematics (DIMA) at the University of Genoa (UniGe). Her teaching responsibilities include courses such as Game Theory, Machine Learning, Optimization and Operations Research, and Operations Research at both undergraduate and master's levels. Her research focuses on optimization theory and its applications in machine learning, inverse problems, and regularization methods. She has contributed to advancements in iterative regularization techniques, stochastic optimization algorithms, and convex optimization frameworks. Her work often bridges theoretical foundations with practical applications in signal processing and data science. Her research interests emphasize structured optimization problems, including low-complexity regularizers, bilevel optimization, and sparse recovery. Key methodologies in her studies include primal-dual dynamics, proximal algorithms, and variance reduction techniques. Recent trends in her publications highlight advancements in unrolled deep networks for sparse signal restoration, adaptive optimization strategies, and convergence analysis of stochastic methods. Villa's collaborative efforts span interdisciplinary projects involving applied mathematics, computer science, and engineering. While no specific awards are listed, her prolific publication record reflects her active role in the optimization and machine learning communities. She has advised multiple research projects but no formal student names are provided in the available data.