جستجوی استاد راهنمای دانشگاهی

Fanny Yang is an Assistant Professor in the Computer Science Department at ETH Zurich . She previously held postdoctoral positions at Stanford University and a Junior Fellowship at the Institute for Theoretical Studies at ETH Zurich, advised by Nicolai Meinshausen . Her PhD was completed at the EECS Department of UC Berkeley , supervised by Martin Wainwright . Research Interests : Theoretical foundations of machine learning and statistics , particularly focusing on overparameterized models and high-dimensional data . Developing trustworthy ML models with emphasis on distributional robustness , domain generalization , and interpretability . Applications in medical diagnostics and treatment effect analysis , aiming to address reliability issues in real-world domains. Recent Work Trends : 2025 Articles : Theoretical analysis of semi-supervised multi-objective learning , test-time scaling with verifiers, and foundation models for efficient randomized experiments . 2024 Articles : Studies on robust mixture learning , privacy-preserving data synthesis via optimal transport , confounding quantification in causal inference , and semi-private learning frameworks. 2023 Articles : Investigations into active vs. passive learning in high dimensions, inductive bias in noisy interpolation , and semi-supervised novelty detection using model ensembles .

• Machine Learning
• Statistics
• Theoretical Machine Learning
• +۷ مورد دیگر

Liza Rebrova is an Assistant Professor in the Department of Operations Research and Financial Engineering (ORFE) at Princeton University's School of Engineering and Applied Science. She is also an associated faculty member of the Program in Applied and Computational Mathematics (PACM) and the Center for Statistics and Machine Learning (CSML). Her research focuses on randomized numerical linear algebra and the mathematics of data science, with connections to high-dimensional probability and stochastic optimization. She develops mathematically justified randomized algorithms for large-scale data, particularly interested in settings where data exhibits mathematical structure such as spectral decay, multi-modality, or non-negativity. Her work addresses challenges in data compression, recovery, and optimization under structured noise conditions. Dr. Rebrova's recent publications show a strong trend toward developing robust algorithms for linear systems, tensor data compression, and nonnegative matrix factorization. Her work bridges theoretical foundations with practical applications in machine learning and data science, with emphasis on memory efficiency and handling corrupted or incomplete data. NSF DMS-2309685 (Single PI, 2024-2026): "Outliers are not what they seem: data-aware, flexible, and robust randomized iterative methods" NSF DMS-2108479 (Collaborative, 2022-2024): "Fast, Low-Memory Embeddings for Tensor Data with Applications" (co-PIs Mark Iwen and Deanna Needell) She currently advises three PhD students (Jackie Lok, Shambhavi Suryanarayanan, and Sofiia Shvaiko) and has previously advised Abraar Chaudhry (PhD 2024) and Nicolo Grometto (Masters thesis 2023). At Princeton, she teaches graduate courses including ORF526 (Graduate Probability), ORF387 (Networks), and ORF523 (Convex and Conic Optimization).

• Mathematics of Data
• Numerical Linear Algebra
• Randomized Algorithms
• +۵ مورد دیگر

Sham Kakade is the Rampell Family Professor of Computer Science and Professor of Statistics at Harvard University, co-director of the Kempner Institute. His research focuses on advancing artificial general intelligence through foundational work in reinforcement learning, large-scale learning systems, and autonomous agent architectures. He earned his PhD in 2003 from the Gatsby Computational Neuroscience Unit at University College London. His work emphasizes scalable optimization algorithms, distributed systems for foundation models, and understanding emergent capabilities in neural architectures. Research interests include full-stack training pipelines for foundation models, mathematical principles of large-scale learning systems, and bridging language models with embodied intelligence. He advises prospective students with backgrounds in applied deep learning or theoretical computer science, offering access to the Kempner Institute's computational resources. He serves on committees for the ACM Prize in Computing and Sloan Research Fellowships, co-organizes the Simons Symposium on Theoretical Machine Learning, and chaired COLT 2011. His lab works at the intersection of theory and practice, addressing challenges in AI's societal impact and technical scalability. Labs/Teams: Co-directs the Kempner Institute, fostering collaborations between AI researchers and social scientists. Active in Harvard's SEAS community.

• Artificial Intelligence
• Machine Learning
• Reinforcement Learning
• +۷ مورد دیگر

Ajit Rajwade is a Professor at the Department of Computer Science and Engineering , Indian Institute of Technology Bombay. His research spans Artificial Intelligence , Compressed Sensing , and Medical Imaging , with affiliations to the Centre for Machine Intelligence and Data Science and the Koita Centre for Digital Health . Education : PhD in Computer and Information Science and Engineering, University of Florida (2010) MSc in Computer Science, McGill University (2004) BTech in Computer Engineering, University of Pune (2002) His research interests focus on intelligent data acquisition, particularly in neural network analysis , graph signal processing , and medical imaging . He develops compressed sensing algorithms for inverse problems like tomography and MRI reconstruction , alongside applying group testing to pandemic response. Scientific awards include the Prof. S. P. Sukhatme Award (2024) and Departmental Teaching Excellence (2019). His publications demonstrate expertise in image restoration , noise modeling , and epidemiological algorithms . He has advised PhD students like Sabyasachi Ghosh and Jerin Geo James , with a focus on computationally efficient methods in medical imaging and machine learning .

• Artificial Intelligence
• Machine Learning
• Signal Processing
• +۶ مورد دیگر

Afonso S. Bandeira is a Professor in the Department of Mathematics (D-MATH) at ETH Zurich, where he conducts research at the intersection of mathematics, statistics, and computer science. He maintains strong affiliations with several interdisciplinary research centers including the Institute For Operations Research (IFOR), the Max Planck ETH Center for Learning Systems, the ETH Foundations of Data Science, and the ETH AI Center, with a courtesy appointment at D-ITET. Bandeira actively teaches courses including Mathematics of Signals, Networks, and Learning, and Mathematics of Data Science. His research focuses on High Dimensional Probability, Random Matrices, Mathematical Statistics, Theoretical Computer Science, Combinatorics, and Mathematical Optimization. Bandeira's work often explores the theoretical foundations of data science, examining phase transitions in statistical problems, computational barriers, and the geometry of high-dimensional spaces. He maintains a research group blog called Randomstrasse101 that emphasizes open problems in his field. Analysis of his recent publications reveals a strong focus on matrix and tensor concentration inequalities, synchronization problems, nonconvex optimization landscapes, and computational-statistical tradeoffs in high-dimensional inference. His work bridges theoretical mathematics with practical applications in machine learning and data analysis, particularly examining where computational limitations arise in statistical problems. Bandeira actively mentors students and researchers, currently supervising several doctoral candidates including Daniil Dmitriev, Konstantin Donhauser, Anastasia Kireeva, Kevin Lucca, Chiara Meroni, Gil Kur, Petar Nizic-Nikolac, and Almut Roedder. He emphasizes that students working with him should participate in the DACO seminar and group meetings, and encourages prospective students to have completed his Mathematics of Signals, Networks, and Learning or Mathematics of Data Science courses. He leads a research group focused on the mathematics of data science, with regular group meetings and seminars. Bandeira has developed comprehensive lecture notes including 'A Tour Through the Mathematics of Signals, Learning, and Networks' (2025) and 'Mathematics of Machine Learning' (2021), and previously authored 'Ten Lectures and Forty-Two Open Problems in the Mathematics of Data Science' (2015).

• High Dimensional Probability
• Random Matrices
• Mathematical Statistics
• +۳ مورد دیگر

Arno De Caigny is an Associate Professor at IÉSEG School of Management in France, specializing in Marketing Analytics. He holds a Ph.D. in Sales and Marketing from the University of Lille and Masters in Economics/Mathematics and Finance from Ghent University. His professional experience includes work as a Business Analyst at Deloitte. His primary research interests include customer churn prediction, AI applications in marketing, explainable AI for business, and life event-based marketing. He develops advanced machine learning models for customer behavior prediction and retention strategies. De Caigny's recent publications demonstrate strong focus on developing interpretable machine learning models for business applications, particularly in customer churn prediction and financial decision support. His work increasingly incorporates deep learning and natural language processing techniques.

• Marketing Analytics
• Customer Behavior
• Machine Learning
• +۳ مورد دیگر

Michal Kolesár is a Professor in the Department of Economics at Princeton University , holding this position since July 2020. Previously, he served as Assistant Professor (2014-2020) with dual appointments in Economics and the Woodrow Wilson School (2018-2020), and as Visiting Assistant Professor at MIT (2016-2017). His research focuses on econometrics , particularly causal inference , instrumental variables , nonparametric regression , and robust statistical methods . His work addresses fundamental challenges in high-dimensional data analysis, treatment effect heterogeneity, and finite-sample inference validity. Current projects include developing bias-aware methods for regularized regression and analyzing dynamic causal effects in nonlinear systems. Kolesár's recent publications reveal a strong emphasis on methodological rigor with practical applications. His work spans instrumental variable techniques (addressing contamination bias, weak identification), regression discontinuity designs (discrete running variables, measurement error), and high-dimensional inference (sparsity fragility, honest confidence intervals). Key recurring themes include finite-sample optimality, coverage probability guarantees, and robustness to model misspecification. Fellow of the International Association for Applied Econometrics (2023) Journal of Econometrics best associate editor award (2023) Sloan Research Fellowship (2019) NSF grants for high-dimensional data inference (2021-2025) and nonparametric regression (2016-2019) Graduate Economics Club teaching awards (2017, 2018) As an educator, Kolesár teaches advanced econometrics courses at both undergraduate (ECO 312, ECO 313) and graduate levels (ECO 517, ECO 519, ECO 539b). He serves as Co-editor of the Journal of Business & Economic Statistics (2024-2027) and sits on editorial boards of Econometrica , American Economic Journal: Applied Economics , and others. His professional activities include extensive peer review for top journals and organization of major econometrics conferences including the 2026 Econometric Society Winter Meeting.

• Econometrics
• Causal Inference
• Instrumental Variables
• +۴ مورد دیگر

Song Mei is an Assistant Professor in the Department of Statistics and Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. She received her Ph.D. from Stanford University in 2020 under Andrea Montanari and maintains active research collaborations with institutions including Amazon (as a 2023 Amazon Research Award recipient) and OpenAI (where she is currently on leave). Her research spans the intersection of statistics, machine learning, information theory, and computer science, with particular emphasis on foundational theories for modern AI systems. Key interests include language models, diffusion models, quantum algorithms, and high-dimensional statistics, often leveraging insights from statistical physics literature. Analysis of her recent publications reveals a strong focus on theoretical underpinnings of generative AI, with significant contributions to understanding contrastive pre-training (CLIP), attention mechanisms in LLMs, and mathematical foundations of diffusion models. Her work demonstrates consistent interdisciplinary connections between statistical theory and practical AI development. Sloan Research Fellowship (2025) Noether Early Career Scholar Award (2025) Google Research Scholar Award (2024) Amazon Research Award (2024) She actively advises graduate students through MA programs and has secured significant research grants including Amazon Research Awards. Her work with AGI Labs at Amazon demonstrates applied impact of theoretical research. Current projects focus on mechanistic interpretability of large language models and mathematical frameworks for generative AI. Professor Mei leads research on the statistical principles behind frontier AI models, with particular focus on developing rigorous theoretical frameworks for understanding emergent behaviors in large-scale systems.

• Language Models
• Diffusion Models
• Theory of Deep Learning
• +۶ مورد دیگر

Jonathan Shihao Ji is an Associate Professor in the School of Computing at the University of Connecticut (UConn), leading the Intelligent Systems Lab. He holds a Ph.D. in Electrical and Computer Engineering from Duke University and previously served as an Associate Professor at Georgia State University and Director of the DoD Center of Excellence (CiARE). His research focuses on deep learning applications in computer vision, NLP, robotics, and high-performance computing, with over 50 publications in top venues like CVPR, NeurIPS, and IEEE journals. He has secured grants from NSF, NIH, DoD, and industry partners including VMware and Nvidia. His work emphasizes efficient algorithms for large-scale data processing, parameter-efficient model fine-tuning (e.g., VB-LoRA), and 3D perception benchmarks for UAVs (UAV3D). Notable contributions include sparse network optimization (Dep-L0), energy-based models (M-EBM), and robust defenses against adversarial attacks (Defense-VAE). He is a Senior Member of IEEE and has developed open-source tools like Parallel Word2Vec and WordRank. Recent projects include accelerating Llama2 models on FPGAs (LlamaF) and improving text-to-image synthesis via contrastive learning. His research spans theoretical advancements and practical applications, with industry collaborations in healthcare, robotics, and embedded systems.

• Deep Learning
• Computer Vision
• Natural Language Processing
• +۵ مورد دیگر

Per Christian Hansen is a Professor at the Department of Applied Mathematics and Computer Science (DTU Compute), Technical University of Denmark (DTU), where he leads the Section for Scientific Computing. He is a VILLUM Investigator and heads the CUQI (Computational Uncertainty Quantification for Inverse Problems) research initiative, aiming to develop accessible computational platforms for uncertainty quantification in inverse problems. His expertise lies in numerical analysis, numerical linear algebra, iterative reconstruction methods, and computational inverse problems, with applications in tomography, signal analysis, and plasma physics. His research integrates theoretical analysis—such as perturbation and convergence analysis—with the development of robust, adaptive, and efficient computational methods. He has co-authored five books, over 100 scientific papers, and several widely used MATLAB software packages, including IR Tools and Regularization Tools. His recent work (2023–2025) emphasizes uncertainty quantification, Bayesian inversion, and high-dimensional tomography in fusion plasmas, reflecting a strong trend toward probabilistic and robust modeling in inverse problems. He is a SIAM Fellow (2015) for his contributions to computational methods for rank-deficient and discrete ill-posed problems and regularization techniques. His scientific leadership is evident in both theoretical advances and practical software implementations. He actively collaborates across disciplines, particularly in nuclear fusion and medical imaging, and continues to supervise PhD students and publish in top-tier journals such as Inverse Problems , SIAM Journal on Scientific Computing , and Nuclear Fusion . SIAM Fellow (2015) VILLUM Investigator He advises PhD and Master’s students in computational mathematics and inverse problems, and his research is supported by major grants, including the VILLUM Investigator award. He leads the CUQI team, which develops open-source tools for non-experts to apply uncertainty quantification in inverse problems. His lab focuses on creating modeling frameworks that bridge theory, computation, and real-world applications in materials science, imaging, and plasma diagnostics.

• Numerical Analysis
• Numerical Linear Algebra
• Iterative Reconstruction Methods
• +۸ مورد دیگر

Rima Alaifari is currently an Assistant Professor for Applied Mathematics at ETH Zürich , where she works on applied analysis, inverse problems, and scientific machine learning. Her research emphasizes stability analysis and regularization of inverse problems, applied harmonic analysis, phase retrieval, and operator learning. She is an associated member of the ETH AI Center and will transition to a full professorship at RWTH Aachen University in 2025 as Chair of Analysis and its Applications. Education : PhD in Mathematics (2010–2014, Vrije Universiteit Brussel); MSc in Applied and Industrial Mathematics (2005–2010, Johannes Kepler University) Research Focus : Stability estimates for inverse problems, phase retrieval in wavelet/Gabor transforms, operator learning with neural networks, and deep learning robustness. Article Trends : Her recent work bridges harmonic analysis with machine learning, focusing on phase retrieval stability, adversarial perturbations in imaging, and mathematically grounded neural operator frameworks like ReNO and CNO. Advising : She has supervised PhD students like Tandri Gauksson and Matthias Wellershoff. Former postdoctoral researchers include Francesca Bartolucci (now at TU Delft) and Jesse Railo (Finnish Inverse Prize winner).

• Applied Analysis
• Inverse Problems
• Scientific Machine Learning
• +۷ مورد دیگر

Dr. Masoumeh Dashti is an Associate Professor in Mathematics at the University of Sussex, UK, affiliated with the School of Mathematical and Physical Sciences. She holds a PhD in Mathematics from the University of Warwick (2008) and prior degrees in Mechanical Engineering from Sharif University of Technology and Tehran Polytechnic. Her research focuses on Partial Differential Equations, Inverse Problems, Bayesian Inference, and their applications in fluid dynamics and epidemiology. Key research interests include: Bayesian approaches to inverse problems, sparsity-promoting estimators, uncertainty quantification, and mathematical modeling of epidemics on networks. She has contributed to foundational work on Besov priors and MAP estimator consistency in nonparametric Bayesian frameworks. Her publications span topics like network inference from epidemic data, contraction rates of posterior distributions, and fluid-structure interaction problems. She has secured grants including 'Two-dimensional stochastically perturbed shallow water equations' (2019-2023) and 'Confronting High Dimensional Network Models With Data' (2018-2022). Currently, she serves as an Associate Editor for SIAM-ASA Journal on Uncertainty Quantification and AIMS Foundations of Data Science . Teaching expertise includes Functional Analysis, Partial Differential Equations, and Calculus of Several Variables at both undergraduate and postgraduate levels.

• Partial Differential Equations
• Inverse Problems
• Bayesian Inference
• +۴ مورد دیگر

Sivaraman Balakrishnan is a Professor at Carnegie Mellon University with joint appointments in the Department of Statistics and Data Science and the Machine Learning Department. His research bridges statistical machine learning, algorithmic statistics, and robust inference. Education: Ph.D. in Computer Science from Carnegie Mellon University (Language Technologies Institute, advised by Jaime Carbonell); postdoctoral work at UC Berkeley (Department of Statistics, advised by Martin Wainwright and Bin Yu). Research Interests: Spanning robust statistics, domain adaptation, minimax hypothesis testing, assumption-light inference, causal inference, statistical optimal transport, non-parametric statistics, ranking, crowdsourcing, optimization, and topological data analysis. Key Research Trends: Recent work focuses on domain adaptation under label/misingness shifts, robust gradient estimation, smooth optimal transport maps, and conditional independence testing. He explores minimax optimal methods, univariate mean estimation, and high-dimensional regression with missing data. Scientific Awards: IMS Lawrence D. Brown Student Award (2021, 2020) NVIDIA Pioneer Award (2018) Franklin V. Taylor Memorial Best Paper Award (2018) Grants and Editorial Roles: NSF grants (CCF-1763734, DMS-1713003, DMS-2113684, DMS-2310632), Amazon Research Award (2021), Google Research Scholar Award (2021). Associate Editor for JASA and JRSSB ; Editorial Board member for Foundations and Trends in Statistics . Collaborative Groups: Co-organizes the Statistics and Machine Learning Reading Group and participates in the Causal Inference Working Group at CMU.

• Statistical Machine Learning
• Algorithmic Statistics
• Robust Statistics
• +۱۱ مورد دیگر

Ivan Selesnick is a Professor of Electrical and Computer Engineering at the NYU Tandon School of Engineering, with joint appointments in Biomedical Engineering and Radiology. He holds affiliations with the Center for Advanced Technology in Telecommunications (CATT) and leads the Selesnick Lab. His research focuses on signal and image processing, sparse signal models, wavelet analysis, and biomedical applications. He received his degrees from Rice University (BS, MEE, PhD in EE) and has been recognized with prestigious awards including the Alexander von Humboldt Fellowship (1997), NSF Career Award (1999), and IEEE Fellow (2016). Education: BS, MEE, and PhD in Electrical Engineering from Rice University (1990, 1991, 1996). He joined NYU Tandon in 1997 and served as a visiting professor at the University of Erlangen-Nuremberg in 1997. Research Interests: Signal Processing, Sparse Signal Models, Wavelet Analysis, Biomedical Signal Processing, and Optimization Techniques. His work emphasizes applications in medicine, imaging, and engineering systems. Awards: In addition to his fellowships, he received the Jacobs Excellence in Education Award (2003) and the Budd Award for Best Engineering Thesis (1996). He has held editorial roles at IEEE Transactions on Image Processing, Signal Processing Letters, and Computational Imaging. Teaching: Courses include Signals, Systems, and Transforms (EE 3054), Digital Signal Processing I/II (EL 6113/EL 7133), Wavelets and Filter Banks (EL 7163), and Biomedical Signal Processing (EL 9133). Labs and Affiliations: Director of the Selesnick Lab, involved in NYU Tandon Future Labs (business incubators) and CATT (telecommunications research). His research spans biomedical sensing, radar signal processing, and algorithm development for medical diagnostics.

• Signal Processing
• Sparse Signal Models
• Biomedical Signal Processing
• +۳ مورد دیگر

Chen Liu is an Assistant Professor in the Department of Computer Science at City University of Hong Kong and the Principal Investigator (PI) of the Machine Learning and Optimization (MLO) group. His research focuses on building reliable machine learning models, particularly studying robustness and privacy properties of deep neural networks from an optimization perspective. University: City University of Hong Kong Academic Rank: Assistant Professor Students: Supervises multiple PhD, MPhil, and postdoctoral researchers. Education: Holds a Ph.D. (2022) and MSc (2017) in Computer Science from École Polytechnique Fédérale de Lausanne (EPFL), and a BSc (2015) in Computer Science from Tsinghua University. Research Interests: Adversarial robustness, privacy-preserving machine learning, optimization algorithms, dataset distillation, generative models, and theoretical analysis of loss landscapes. His work addresses challenges like catastrophic overfitting, architecture overfitting in distilled data, and stable adversarial training methods. Article Trends: Recent publications explore adversarial robustness under l0/l1 norms, gradient inversion for data reconstruction, evolutionary factor searching in finance, and meta-tuning for out-of-domain few-shot learning. These works emphasize optimization techniques to enhance model reliability and generalization. Scientific Awards: Microsoft Research Ph.D. Scholarship Programme (2017–2019) Advising and Grants: Supervises a diverse team of current and former students, with collaborations across institutions like George Mason University and Zhejiang University. Research supported by academic and industry grants. Labs and Teams: Leads the MLO group, which investigates fundamental ML theory and algorithms to improve system reliability. The group's work spans adversarial training, dataset distillation, and generative model optimization.

• Machine Learning
• Adversarial Robustness
• Privacy-Preserving Machine Learning
• +۹ مورد دیگر