جستجوی استاد راهنمای دانشگاهی

• Neural Networks
• Optimization Theory
• Deep Learning
• +۳ مورد دیگر

Ruoyu Sun is an Adjunct Associate Professor in the Department of Industrial and Enterprise Systems Engineering at the University of Illinois at Urbana-Champaign. His research focuses on neural networks, optimization theory, and deep learning. He has received the NSF CRII Award (2018) for his contributions to engineering research. His work explores topics such as gradient regularization in GANs, global convergence analysis of meta-learning algorithms, and theoretical properties of neural network architectures. Recent collaborations include studies on sparse network landscapes and optimization challenges in deep learning systems. Ruoyu Sun's research has been published in top venues such as the SIAM Journal on Optimization and the IEEE Conference on Computer Vision and Pattern Recognition. His work bridges theoretical analysis with practical applications in machine learning and artificial intelligence.

Ioannis Kosmidisمشاهده پروفایل

استاد

• Statistics
• Machine Learning
• Data Science
• +۶ مورد دیگر

Ioannis Kosmidis is a Professor of Statistics at the University of Warwick and a Turing Fellow of The Alan Turing Institute. He holds an honorary professorship at University College London. His academic journey includes a BSc from Athens University of Economics and Business (2004) and a PhD in Statistics from the University of Warwick (2007). He has held roles such as Turing University Lead and Turing Liaison at Warwick, contributing to the institution's collaboration with The Alan Turing Institute. His research focuses on statistical methodology, including bias reduction in models, high-dimensional statistics, and applications in sports science, neuroimaging, finance, and earthquake engineering. He has developed influential R packages like brglm2 and cranly , emphasizing software development for statistical computing. Prof. Kosmidis has supervised numerous PhD students and postdocs, fostering interdisciplinary collaborations. His work spans over 111 presentations across 59 cities, highlighting his international academic engagement. Key achievements include advancing bias reduction techniques and applying statistical methods to real-world challenges like seismic vulnerability assessment and financial modeling.

Shaoning Hanمشاهده پروفایل

استادیار

• Mathematical Optimization
• Mixed-Integer Nonlinear Programming
• Nonsmooth Optimization
• +۳ مورد دیگر

Shaoning Han is a Presidential Young Professor (Assistant Professor) in the Department of Mathematics and the Institute of Operations Research and Analytics (IORA) at the National University of Singapore (NUS). He previously held a postdoctoral position at the University of Southern California (USC), working under Prof. Jong-Shi Pang. His research focuses on mathematical optimization, including mixed-integer nonlinear programming, nonsmooth optimization, and their applications in operations research and data science. Han earned his Ph.D. in Industrial Engineering from USC under Prof. Andrés Gómez and a B.S. in Mathematics from the University of Science and Technology of China (USTC). His work emphasizes advancing optimization methodologies, particularly for problems involving complementarity constraints, indicator variables, and sparsity. Recent contributions include progressive MIP methods for indefinite QPs, real-time solutions for banded matrix problems, and convexification techniques for nonconvex optimization. Han is actively recruiting PhD students interested in mathematical optimization. Research Highlights: His articles span theoretical advances (e.g., epi-stationarity analysis, parametric variational inequalities) and applied frameworks (e.g., robust SVMs, binarized neural networks). Key themes include polynomial-time solvability of MRFs, convex relaxations for low-rank functions, and sparse signal estimation. Awards: Third Place, INFORMS JFIG Paper Competition (2023) Journal of Global Optimization Best Paper Honorable Mention (2023) Teaching: Courses include MA5243 (Advanced Mathematical Programming) and MA3252 (Linear and Network Optimization). Labs/Teams: Active member of IORA, NUS’s Smart Nation Research Cluster.

• Watermarking Generative AI
• Differential Privacy
• Reinforcement Learning
• +۳ مورد دیگر

Yu-Xiang Wang is Associate Professor at UC San Diego's Halıcıoğlu Data Science Institute and Department of Computer Science and Engineering. He directs the S2ML Lab, focusing on machine learning theory and applications in privacy, reinforcement learning, and generative AI. His research develops provable algorithms for watermarking AI content, practical differential privacy, offline RL, and adaptive deep learning. Current NSF projects investigate adaptivity in neural networks and privacy-preserving ML. Publications address watermark robustness, differential privacy optimization, neural collapse phenomena, and sparse model training. Recent advances include privacy-preserving generative AI detection and adaptive algorithms for nonstationary environments. Honored with NSF CAREER award and paper awards (NeurIPS Spotlight, ICML Oral), he teaches graduate courses in machine learning and differential privacy. Research applications span healthcare, finance, and AI safety.

Xin Tongمشاهده پروفایل

دانشیار

• Asymmetric Statistical Learning
• Neyman-Pearson Classification
• High-dimensional Statistics
• +۵ مورد دیگر

Xin Tong is an Associate Professor in the Department of Data Sciences and Operations at the Marshall School of Business, University of Southern California. His research focuses on asymmetric statistical learning, Neyman-Pearson classification, high-dimensional statistics, and network analysis. He holds a PhD in Operations Research from Princeton University (2012) and a B.S. in Mathematics from the University of Toronto (2007). Key contributions include developing Neyman-Pearson classification frameworks for imbalanced datasets and advancing spectral clustering techniques. His work has been supported by NSF grants and NIH funding. Tong serves as an Associate Editor for the Journal of the American Statistical Association and Journal of Business and Economic Statistics. Recent research highlights include studies on label-noise-adjusted classification algorithms, citation network analysis, and fairness-adjusted machine learning. He teaches courses on modern statistical learning and GenAI/ML strategies for business transformation. Notable awards include the Zellner Thesis Award (2013) and multiple NSF grants. His lab's work bridges statistical theory with applications in genomics, social networks, and healthcare risk assessment.

Rob Masterمشاهده پروفایل

استاد مدعو

• Digital Marketing
• AI and Machine Learning
• Brand Management
• +۳ مورد دیگر

Rob Master is an Adjunct Professor at the University of Wisconsin–Madison and currently serves as Vice President of Media and Digital Engagement for North America at Unilever, where he leads teams driving innovation in media strategy and integrated communication plans for global brands. He also holds the role of Senior Advisor at McKinsey & Company. Master has over two decades of experience in brand marketing, spanning roles at PepsiCo, Unilever, and multiple startups, focusing on award-winning campaigns for brands like Dove and Axe. Master holds a B.A. in Political Science from the University of Wisconsin–Madison and an M.B.A. from the Olin School of Business at Washington University in St. Louis. His professional achievements include leading Unilever to accolades such as Advertising Age's Digital Marketer of the Year and Media Post's Media Client of the Year. His academic contributions span AI and machine learning, with a focus on neural networks, generative models, and data-driven strategies. His research interests bridge theoretical advancements in AI (e.g., in-context learning, multitask learning) and applied domains like media strategy and consumer behavior. Key themes include optimizing neural network architectures, improving model robustness, and leveraging human-AI collaboration for creative tasks like humor generation. Master's recent publications (2023–2025) emphasize innovations in deep learning, active learning strategies, and the intersection of AI with marketing and media. His work often explores scalability, efficiency, and ethical considerations in AI deployment.

Robert Nowakمشاهده پروفایل

استاد

• Signal Processing
• Machine Learning
• Optimization
• +۳ مورد دیگر

Robert Nowak is a Professor of Electrical and Computer Engineering at the University of Wisconsin-Madison, holding the Nosbusch Professorship in Engineering. His research focuses on signal processing, machine learning, optimization, and statistics, with notable contributions to neural networks, active learning, and in-context learning. He is affiliated with the School of Computer, Data & Information Sciences and collaborates on interdisciplinary projects involving AI, human-computer interaction, and vision systems. His work spans theoretical advancements in approximation theory, regularization techniques, and neural network architecture design, alongside applied topics like humor analysis in AI, recommendation systems, and OOD detection. Recent publications emphasize multi-task learning, generative models, and scalable data filtering systems. Nowak’s research intersects machine learning foundations and practical applications, with a focus on improving data efficiency, generalization, and human alignment in AI systems. He leads projects on active learning strategies for open-world scenarios and develops frameworks for label-efficient learning.

Rahul Parhiمشاهده پروفایل

استادیار

• Machine Learning
• Neural Networks
• Signal Processing
• +۹ مورد دیگر

Rahul Parhi is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of California, San Diego (UCSD), where he has been since 2024. Previously, he was a postdoctoral researcher at the École Polytechnique Fédérale de Lausanne (EPFL) from 2022 to 2024, and completed his Ph.D. in Electrical Engineering at the University of Wisconsin–Madison in 2022. His research focuses on the mathematics of data science, particularly the theoretical foundations of neural networks and deep learning, with a strong emphasis on functional/harmonic analysis, signal processing, and nonparametric statistics. Key research themes include the mathematics of computed tomography, sparsity, compressed sensing, and the geometry of Banach spaces. Education: B.S. in Mathematics, University of Minnesota, Twin Cities (2018) B.S. in Computer Science, University of Minnesota, Twin Cities (2018) Ph.D. in Electrical Engineering, University of Wisconsin–Madison (2022) His research interests span the interplay between functional and harmonic analysis with data science, including: Foundations of neural networks and deep learning Approximation properties of neural networks Nonparametric statistical estimation Inverse problems and compressed sensing Wavelet-based signal processing Banach space theory His recent publications explore topics such as neural network optimization, attention mechanisms, and the theoretical limits of learning in high-dimensional spaces. He has contributed to understanding the mathematical principles underlying deep learning's success in breaking the curse of dimensionality. His work bridges abstract mathematical concepts with practical applications in signal processing and machine learning. Parhi's research also extends to collaborative projects with experts in optimization and applied mathematics, aiming to develop novel algorithms with rigorous theoretical guarantees. His lab at UCSD focuses on advancing interdisciplinary research at the intersection of mathematics and data science.

• Statistical Data Analysis
• Matrix Estimation
• Network Models
• +۶ مورد دیگر

Olga Klopp is a Professor at ESSEC Business School in France, specializing in statistical data analysis and network modeling. She holds academic positions including Associate Professor (2017–2023) and has been a member of CNRS and CREST. Her research focuses on matrix estimation, network models, and high-dimensional statistics, with contributions to graphon estimation, robust matrix completion, and change-point detection. Klopp has received prestigious awards like the Fulbright Scholar Award (2025) and Beaufort Fellowship (2024). She co-directs theses, such as guiding Solenne Gaucher’s 2022 thesis. Klopp organizes conferences like the 2025 Graph Neural Networks workshop and serves on editorial boards, including Bernoulli Journal. Her teaching includes courses on statistical inference and big data analytics. Education: HDR (2016, Université Paris X Nanterre) Ph.D. in Mathematics (2004, UNAM Mexico) Master in Mathematics (1997, Lomonosov Moscow State University) Research Interests: Network models, sparse graphon estimation, matrix completion, robust statistics, and machine learning applications in networks. Awards: Fulbright Scholar Award (2025), Beaufort Fellow (2024). Grants/Advising: Co-director of Solenne Gaucher’s thesis (2022), involved in organizing conferences and seminars on mathematical statistics and networks. Labs/Teams: Active in ESSEC’s Information Systems department, collaborating with institutions like CentraleSupelec and ENSAE.

Marcello Carioniمشاهده پروفایل

استادیار

• Optimal Transport
• Inverse Problems
• Machine Learning
• +۴ مورد دیگر

Marcello Carioni is an Assistant Professor in Mathematics at the University of Twente, affiliated with the Mathematics of Imaging & AI (MIA) group and the SACS group within the Faculty of Electrical Engineering, Mathematics and Computer Science. His research focuses on optimal transport theory, inverse problems, calculus of variations, and their applications in machine learning and imaging. He holds a PhD in Mathematics from the Max-Planck Institute for the Mathematics in the Sciences (Leipzig), preceded by a M.S. and B.S. in Mathematics from the University of Parma. Education: B.S. (2009, University of Parma), M.S. (2012, University of Parma), PhD (2017, Max-Planck Institute) Research interests include: Dynamic optimal transport and preferential path analysis Sparsity in variational regularization Applications to medical imaging and neural networks Generalized conditional gradient methods Recent work emphasizes sparsity optimization for dynamic inverse problems, Lipschitz spaces in neural networks, and end-to-end reconstruction techniques. His 2025 preprints explore Wasserstein curves and distributionally robust optimization. He has advised PhD students including Christian Amend (2024) and Floor van Maarschalkerwaart (2024).

Yiqi (Annie) Tangمشاهده پروفایل

استادیار

• High-dimensional Statistics
• Bayesian Statistics
• Conformal Prediction
• +۳ مورد دیگر

Annie Tang is an Assistant Professor in the Statistics Department at Colby College, Waterville, ME. Her research spans both theoretical and applied statistics, with a focus on high-dimensional data analysis and Bayesian methodologies. She earned her PhD in Statistics from North Carolina State University under the supervision of Ryan Martin. Dr. Tang's research interests encompass high-dimensional statistics, Bayesian and Bayesian-adjacent methods, conformal prediction, variational inference, and foundational statistics. She applies these methods to health services research, including population health and sepsis outcomes. Her work often addresses sparse modeling and empirical prior methods to improve statistical inference in complex datasets. Analysis of her recent publications (2020-2025) reveals a strong focus on developing novel Bayesian and empirical Bayes techniques for high-dimensional problems, with increasing applications in healthcare. Her research bridges theoretical statistics and real-world health policy questions, particularly in sepsis mortality and regional healthcare variation. She has also contributed software tools such as the R package 'ebreg'.

Nicolas Flammarionمشاهده پروفایل

استادیار

• Machine Learning
• Statistics
• Optimization
• +۳ مورد دیگر

Nicolas Flammarion is a tenure-track Assistant Professor in Computer Science at the École Polytechnique Fédérale de Lausanne (EPFL). He holds positions in multiple departments including the Theory in Machine Learning (TML) lab under the School of Computer and Communication Sciences (IC). His roles include teaching and doctoral program leadership across disciplines like Communication Systems and Computer Science. Education: PhD in 2017 from École Normale Supérieure (Paris), advised by Alexandre d’Aspremont and Francis Bach. Postdoctoral fellowship at UC Berkeley under Michael I. Jordan. Research focuses on machine learning theory, optimization, and statistical methods. Key areas include adversarial robustness, algorithmic generalization, and optimization dynamics. Notable contributions include work on SGD/GD comparisons, adversarial benchmarking (RobustBench), and safety in AI systems. Awards include the 2018 Fondation Mathématique Jacques Hadamard PhD Prize, 2021 NeurIPS Outstanding Paper Award, and 2024 Trust & Safety Google Research Award. Supervises PhD students in topics like algorithm design and machine learning theory. Labs/Teams: Leads TML lab and contributes to EPFL's doctoral programs in Informatics and Communication Sciences. Active in curriculum development for advanced machine learning topics.

• Control Systems
• Artificial Intelligence
• Mathematical Optimization
• +۵ مورد دیگر

Giuseppe Carlo Calafiore is a Professor at the Polytechnic University of Turin, Italy, specializing in control systems, optimization, and their applications in finance, robotics, and machine learning. His work bridges theoretical advancements with practical implementations, focusing on stochastic systems, financial networks, and neural networks. He has contributed to methodologies for robust optimization, model predictive control, and distributed algorithms. Key research areas include system identification, energy systems optimization, and applications of control theory in epidemic modeling and financial contagion analysis. His research interests span control systems, artificial intelligence, mathematical optimization, and their intersections with financial engineering and robotics. Notable contributions include techniques for nonlinear system identification, robust resource allocation in telecommunications, and optimal clearing payment models in financial networks. He has also developed algorithms for distributed sensor networks and multi-agent systems, emphasizing scalability and reliability. Recent work explores sparse neural network architectures, federated learning convergence, and vaccination campaign planning under uncertainty. His interdisciplinary approach integrates tools from probability theory, convex optimization, and game theory, with applications in energy systems, robotics, and public health.

• Radio Astronomy
• Medical Imaging
• Compressed Sensing
• +۳ مورد دیگر

Yves Wiaux is a Professor at Heriot-Watt University's School of Engineering & Physical Sciences, affiliated with the Institute of Sensors, Signals & Systems. He specializes in advanced signal processing techniques with applications in radio astronomy and medical imaging. His research focuses on compressed sensing, optimization algorithms, and imaging methods for radio interferometry and MRI. His work integrates mathematical frameworks like wavelet transforms and sparse regularization to address challenges in high-dimensional data reconstruction. Notable contributions include the development of algorithms like SARA (Sparsity Averaging Reweighted Analysis) and PURIFY for radio interferometric imaging, as well as applications in medical imaging such as magnetic resonance fingerprinting. Wiaux collaborates extensively in international projects, including the LOFAR Two Meter Sky Survey. He advises PhD students through the BASP (Biomedical and Astronomical Signal Processing) group and leads research initiatives in scalable imaging techniques for large datasets.

Vincent Vuمشاهده پروفایل

دانشیار

• High-Dimensional Data Analysis
• Statistical Learning
• Statistical Computing
• +۳ مورد دیگر

Vincent Vu is an Associate Professor of Statistics at The Ohio State University, affiliated with the Department of Statistics. He holds a PhD from the University of California, Berkeley (2009). His research focuses on high-dimensional statistics, statistical machine learning, and their applications in neuroimaging, particularly fMRI. He previously worked as a software engineer in Silicon Valley for over six years, blending computational and statistical expertise. His expertise includes statistical computing, multivariate analysis, and computational sufficiency. He has been funded by the NSF and received the 2012 AISTATS Best Paper Award. He serves as an associate editor for the Journal of the American Statistical Association and The American Statistician. His work bridges statistical theory and computation, addressing challenges in high-dimensional data analysis. Collaborations involve neuroscientific applications, combining algorithmic innovation with real-world problem-solving.