Find Academic Supervisors

• High-dimensional probability theory
• Data Science
• Machine Learning
• +5 more

Sjoerd Dirksen is a Professor of Mathematics for Data Sciences at Utrecht University since May 2025, having previously served as an Associate Professor for Applied Mathematics (2019-2025) and Junior Professor at RWTH Aachen University (2014-2019). He is affiliated with the Mathematical Institute within the Faculty of Science at Utrecht University, where his office is located in the Hans Freudenthal Building. His research interests focus on high-dimensional probability theory and its applications in data science, machine learning, and signal processing. Specifically, he investigates randomized data dimension reduction methods using structured random matrices, theory for deep learning including random neural networks, high-dimensional covariance estimation for wireless communication systems, and statistical postprocessing of weather forecasts in collaboration with the Royal Netherlands Meteorological Institute (KNMI). Previously, he worked on compressed sensing, sharp estimates for stochastic processes in Banach spaces, and noncommutative analysis. Analysis of his recent publications (2018-2024) reveals a strong focus on quantization effects in high-dimensional data processing, particularly one-bit compressed sensing and covariance estimation under coarse quantization. His work bridges theoretical mathematics with practical applications in signal processing, wireless communications, and meteorological forecasting, demonstrating a consistent trajectory from foundational mathematical research to applied data science problems. Dirksen's academic career shows progression from postdoctoral work at the Hausdorff Center for Mathematics in Bonn to independent research positions. His publication record demonstrates significant contributions to the mathematics of data science, with papers appearing in top journals across mathematics, statistics, and signal processing. His research combines deep theoretical insights with practical applications, particularly in the areas of dimensionality reduction and high-dimensional statistics.

Valentina BreschiView profile

Assistant Professor

• Data-driven control
• Control systems
• Machine learning
• +5 more

Valentina Breschi is an Assistant Professor in the Control Systems Group at the Department of Electrical Engineering, Eindhoven University of Technology (TU/e). She holds a Ph.D. from IMT School for Advanced Studies Lucca, with postdoctoral and junior faculty experience at Politecnico di Milano. Her research focuses on data-driven control, jump model learning, meta-learning for system identification, and human-centered policy design for mobility systems. She contributes to UN Sustainable Development Goals related to sustainable infrastructure and innovation. Education: B.Sc. in Electronic and Telecommunication Engineering (University of Florence, 2011) M.Sc. in Electrical and Automation Engineering (University of Florence, 2014) Ph.D. in Control Systems (IMT School for Advanced Studies Lucca, 2018) Research Interests: Her work spans data-driven control methodologies, including LPV control, predictive control, and ethical frameworks for policy design. She explores applications in sustainable mobility, energy systems, and healthcare, emphasizing fairness and social impact. Labs/Teams: She is part of the Control Systems Group, collaborating on projects like the CONSIDER study and the design of fair-MPC frameworks. Her work integrates theoretical control principles with real-world applications in smart systems and social networks.

Alex TownsendView profile

Associate Professor

• Applied Mathematics
• Numerical Analysis
• Scientific Computing
• +6 more

Alex Townsend is an Associate Professor of Mathematics at Cornell University, affiliated with the College of Arts and Sciences. He holds the Stephen H. Weiss Junior Fellowship and has been recognized for both research and teaching excellence. His research focuses on numerical analysis, scientific computing, and theoretical aspects of deep learning, with contributions to spectral methods, low-rank techniques, and computational algebraic geometry. Education: Townsend earned a DPhil (PhD) in Mathematics from the University of Oxford in 2014. Research Interests: Townsend's work spans several areas: novel spectral methods for differential equations, low-rank matrix and tensor techniques, theoretical foundations of deep learning, and computational algebraic geometry. His research emphasizes developing fast, accurate, and robust numerical algorithms with applications in science and engineering. Teaching & Mentoring: Townsend is a dedicated educator, having taught courses at MIT and Cornell on topics ranging from linear algebra and numerical analysis to advanced graduate-level subjects like kernel-based learning and top-ten algorithms of the 20th century. He has mentored numerous PhD students and postdocs, many of whom now hold academic and industry positions. Awards & Honors: 2022 Stephen H. Weiss Teaching Award 2022 Simons Fellowship in Mathematics 2018 SIAG/LA Early Career Prize 2015 Leslie Fox Prize in Numerical Analysis Grants & Funding: Townsend has secured significant funding, including an NSF CAREER grant (2021), to support his work on operator learning and spectral methods. Labs & Collaborations: While not tied to a specific lab, his research frequently intersects with computational mathematics and machine learning communities. He collaborates widely, contributing to open-source tools like Chebfun and Diskfun.

• Mathematical Data Science
• Machine Learning
• Compressed Sensing
• +5 more

Johannes Maly is an Assistant Professor at the Bavarian AI Chair for Mathematical Foundations of Artificial Intelligence at LMU Munich. He previously held postdoctoral positions at Catholic University of Eichstaett-Ingolstadt and RWTH Aachen University, and completed his PhD at TUM Munich under Prof. Massimo Fornasier. PhD in Mathematics (2019, TUM Munich) M.Sc. in Mathematics (2015, TUM Munich) B.Sc. in Mathematics (2013, TUM Munich) His research focuses on mathematical data science and machine learning, specifically addressing: Robust covariance estimation under quantization Neural network approximation properties Implicit bias in gradient descent training Multi-structured signal recovery Quantization effects in deep learning and compressed sensing His recent publications analyze dithered quantization in covariance estimation, implicit regularization in overparameterized models, and multi-structured data recovery. He applies mathematical rigor to practical challenges in wireless communications (e.g., MIMO systems) and neural network training. Scientific recognition includes: relAI Fellow MCML Associate He supervises code/toolbox development for reproducibility and teaches graduate courses in convex optimization, high-dimensional probability, and mathematical data science. His work bridges theoretical mathematics and applied signal processing.

Mathukumalli VidyasagarView profile

Professor

• Machine Learning
• Systems and Control Theory
• Computational Biology
• +4 more

Mathukumalli Vidyasagar is a Distinguished Professor at the Indian Institute of Technology Hyderabad and previously held the SERB National Science Chair and Cecil & Ida Green Chair in Systems Biology Science at the University of Texas at Dallas. He earned his Ph.D. from the University of Wisconsin, Madison, and has authored 13 books and over 160 peer-reviewed papers.

Boris LandaView profile

Assistant Professor

• Statistical Signal Processing
• Geometric Data Analysis
• Manifold Learning
• +5 more

Boris Landa is an Assistant Professor in the Department of Electrical & Computer Engineering at Yale University. His research focuses on statistical signal processing and geometric data analysis, developing theoretical and computational tools for analyzing large, complex datasets. He holds a Ph.D. and M.S. from Tel Aviv University, Israel, and a B.S. from the Technion - Israel Institute of Technology. His work bridges computational methods with applications in molecular biology, cryo-electron microscopy, and high-dimensional data analysis. Notable contributions include robust inference of manifold geometry, doubly stochastic scaling techniques, and multi-reference factor analysis for alignment problems. Recent research explores optimal transport metrics for single-cell data and noise stabilization in signal recovery. Landa's publications span prestigious journals such as SIAM Journal on Mathematics of Data Science and Information and Inference. His methodologies address challenges in manifold learning, graph Laplacian normalization, and biological dataset integration. Active areas include developing adaptive algorithms for low-rank signal detection and robust statistical techniques for heterogeneous data. His educational background includes advanced studies in applied mathematics and engineering, with a strong emphasis on interdisciplinary applications. Ongoing projects involve geometric approaches to omics data analysis and scalable solutions for large scientific imaging datasets.

R RaviView profile

Professor

• Discrete Optimization
• Operations Research
• Computer Science
• +4 more

R Ravi is the Vasantrao Dempo Professor of Operations Research and Computer Science at Carnegie Mellon University's Tepper School of Business. He holds a B.E. from IIT Madras and M.S./Ph.D. from Brown University. Active since 1995, he served as Associate Dean for Intellectual Strategy and Chair of the Future Educational Delivery Committee. He currently directs Analytics Strategy and leads the Center for Intelligent Business. His research focuses on discrete optimization, network optimization, and applications in supply chain logistics and online advertising, supported by NSF, Google, and others. He has advised over two dozen doctoral students and developed graduate courses like Network Optimization. He received the 30-year Test of Time Award (2023) and is an INFORMS Fellow. His academic roles include editorial leadership in Operations Research and FOCS chairmanship.

• Bioprocess Engineering
• Downstream Processing
• Industrial Biotechnology
• +7 more

Rainer Hahn is an Associate Professor in Biochemical Engineering at the Institute of Biochemical Engineering, Department of Biotechnology and Food Sciences, University of Natural Resources and Life Sciences, Vienna (BOKU). He also serves as Head of the Downstream Processing Unit at the BioIndustrial Pilot Plant and is a key researcher at the Austrian Center of Industrial Biotechnology (ACIB). His work is centered on bioprocess engineering with a strong focus on downstream processing and biopharmaceutical purification. University: University of Natural Resources and Life Sciences, Vienna (BOKU) School: Department of Biotechnology and Food Sciences Department: Institute of Biochemical Engineering Role: Associate Professor, Head of Downstream Processing Unit His research interests span Bioprocess Engineering , Downstream Processing , Industrial Biotechnology , Pharmaceutical Technology , and Chemical Biology . He investigates advanced purification techniques, particularly in chromatography and protein separation processes. His recent work emphasizes multicomponent adsorption, protein A affinity systems, and purification of complex biomolecules like secretory immunoglobulin A (sIgA). The trend in his recent publications reveals a strong emphasis on protein purification , chromatographic modeling , and process optimization in biopharmaceutical manufacturing. His work integrates experimental analysis with mathematical modeling to improve efficiency and predictability in downstream operations, especially in multi-component systems. Topics such as continuous chromatography , pH transients , and affinity resin development reflect his leadership in advancing industrial bioprocessing. His notable scientific awards include: HOUSKA PRIZE (Recognition Award) - 2016 Dissertation Prize of the Austrian Society for Biotechnology - 2002 Rainer Hahn has been actively involved in numerous research projects funded by FWF, national enterprises, and private foundations, focusing on biopharmaceutical purification and process development. He mentors students and contributes to academic training through lectures and supervision. He is also a dedicated reviewer for leading journals such as Journal of Chromatography A , Biotechnology and Bioengineering , and Separation and Purification Technology . His work is closely tied to industrial applications, particularly in the development of scalable and efficient biomanufacturing processes. He is associated with the BioIndustrial Pilot Plant and collaborates with ACIB, contributing to innovation in industrial biotechnology. His research group focuses on developing robust downstream strategies for next-generation biopharmaceuticals.

Ming YanView profile

Associate Professor

• Optimization Methods
• Sparse Recovery
• Inverse Problems
• +7 more

Ming Yan is an Associate Professor and Assistant Dean at the School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), where he has been serving since 2022. Prior to this position, he was an Associate Professor at Michigan State University from 2021 to 2023 (on leave from 2022 to 2023) and an Assistant Professor from 2015 to 2021. His academic journey includes postdoctoral positions at UCLA and Rice University. His educational background includes: Ph.D. in Mathematics from University of California, Los Angeles (UCLA), 2012 M.S. in Mathematics from University of Science and Technology of China (USTC), 2008 B.S. in Mathematics from University of Science and Technology of China (USTC), 2005 Ming Yan's research focuses on optimization methods , particularly for sparse recovery and inverse problems . His work extends to federated and machine learning algorithms , parallel and distributed algorithms for large-scale data , and variational techniques in image processing . His approach often combines theoretical analysis with practical applications, developing algorithms that address computational challenges in modern data science. His recent publications demonstrate a strong focus on decentralized optimization , primal-dual algorithms , and sparse recovery techniques . These works span theoretical developments in convergence analysis and practical applications in machine learning and signal processing. His research has evolved from foundational work in image processing to more recent contributions in distributed learning and federated systems, reflecting the changing landscape of data science. Ming Yan is actively involved in mentoring students and has indicated that he is recruiting Ph.D. students, postdocs, and visiting students at CUHK-Shenzhen. His teaching portfolio includes courses in calculus, optimization, and computational methods across multiple institutions. His research is supported by various grants, though specific details are not provided in the available information. He has developed several algorithms and software implementations, including the PD3O framework for convex optimization algorithms.

Igor MolybogView profile

Assistant Professor

• Artificial Intelligence
• Large Language Models
• Multimodal Modeling
• +5 more

Igor Molybog is an Assistant Professor at the University of Hawai'i at Manoa, holding joint appointments in the Departments of Electrical and Computer Engineering and Information and Computer Sciences. His research focuses on advancing artificial intelligence, particularly through large language models (LLMs), multimodal modeling, and core machine learning optimization. He leads the HawAII research group, exploring applications like LLM alignment, efficient inference systems, and scaling properties of foundation models. Education: Ph.D. in Engineering from UC Berkeley (2022), specializing in optimization algorithms for complex systems. Previously worked at Meta AI on LLaMa model development. Research Interests: Efficient LLM development and evaluation frameworks Multimodal AI integration (video/audio + text) Scalable optimization for large models Computational efficiency in training/ inference Recent Work: Presented REAL alignment method (2024), developed long-context scaling techniques (2023), contributed to Llama 2 chat models (2023). Collaborates with organizations like Epoch AI on scaling challenges. Teaching: Offers courses in AI, machine learning, and optimization across ECE and ICS departments. Labs/Teams: Leads HawAII Initiative fostering AI collaboration at UH Manoa, organizes paper reading seminars, and hosts technical talks with industry experts.

Tianqi HongView profile

Assistant Professor

• Power Systems
• Power Electronics
• Renewable Energy Integration
• +4 more

Dr. Tianqi Hong is an Assistant Professor at the University of Georgia, affiliated with the School of Electrical & Computer Engineering and the Department of Electrical and Computer Engineering. He holds a B.Sc. from Hohai University (2011), an M.Sc. from Southeast University and NYU (201?), and a Ph.D. from NYU (2016). Prior to his academic role, he served as a Principal Energy System Scientist at Argonne National Laboratory and a Senior Research Scientist at Unique Technical Services, LLC. His research focuses on power systems, power electronics, renewable energy integration, and AI-driven solutions for smart grids. Dr. Hong’s work emphasizes cybersecurity for power infrastructure, nonlinear dynamics in microgrids, and advanced control strategies. He actively contributes to IEEE Transactions across multiple journals and chairs the IEEE IAS Industrial Power Converters Committee. His recent publications address topics like AI-based photovoltaic inverter modeling, cyberattack mitigation in smart grids, and voltage regulation using distributed optimization. He has authored over 60 peer-reviewed articles, spanning from 2014 to 2025, with a focus on energy system stability, renewable integration challenges, and data-driven methodologies. His professional service includes editorial roles in top-tier journals and leadership in industry-research collaborations.

Julian TachellaView profile

Researcher

• Signal Processing
• Machine Learning
• Computational Imaging
• +5 more

Dr. Julian Tachella is a CNRS Research Scientist at the Sisyph Laboratory of École Normale Supérieure de Lyon, with co-founder/CSO roles at Blur Labs. His career spans signal processing, machine learning, and computational imaging, focusing on inverse problems and self-supervised learning. Affiliation: CNRS (French National Centre for Scientific Research), Sisyph Laboratory, École Normale Supérieure de Lyon Co-founder & CSO: Blur Labs (AI/Imaging startup) Research Interests: At the intersection of signal processing and deep learning , his work addresses imaging inverse problems through self-supervised methodologies (e.g., UNSURE, Generalized R2R) that eliminate ground-truth requirements. Key contributions include equivariant imaging frameworks for stability, spline sketches for photon-counting lidar compression, and uncertainty quantification techniques with equivariant bootstrapping. Recent Trends: 2025 publications emphasize lightweight architectures for multi-domain reconstruction (CT, super-resolution) and noise-agnostic SURE methods. 2024 works focus on audio declipping , compressed lidar , and nonlinear algorithm unrolling with applications in autonomous vehicles and medical imaging. Scientific Awards: Best Student Paper Award at ICASSP’22 Collaborations & Leadership: He leads the DeepInverse open-source project and develops algorithms for real-time 3D lidar reconstruction. His team includes researchers from University of Edinburgh and Grenoble INP, with applications in automotive lidar and underwater imaging.

Aravindan VijayaraghavanView profile

Associate Professor

• Theoretical Computer Science
• Machine Learning Theory
• Data Science
• +7 more

Aravindan Vijayaraghavan is an Associate Professor in the Department of Computer Science at Northwestern University (affiliated with McCormick School of Engineering). He also holds courtesy appointments in the Industrial Engineering and Management Sciences (IEMS) department. Research interests include theoretical computer science , machine learning algorithms , quantum information , and combinatorial optimization under non-worst-case paradigms. He leads IDEAL (Institute for Data, Economics, Algorithms and Learning) as Site Director at Northwestern and former Institute Director (2023-24). Academic Background : PhD in Computer Science from Princeton University (advisor: Moses Charikar ) Bachelor's Degree in Computer Science from Indian Institute of Technology Madras Postdoctoral work at Courant Institute (NYU) and Carnegie Mellon University via Simons Collaboration grants Research Contributions : Developed smoothed analysis frameworks for random matrices with dependent entries Created sum-of-squares certificates for anti-concentration beyond Gaussian distributions Advanced quantum entanglement certification algorithms for subspaces Improved weak-to-strong generalization theory with data distribution expansion properties Designed error-tolerant e-discovery protocols for legal document classification Scientific Recognition : NSF CAREER Award NSF AITF Award (CCF-1637585, CCF-2154100) Google Research Scholar Program grant Amazon Research Awards program support Simons Postdoctoral Fellowship Academic Leadership : General Chair for FOCS 2024 Co-organizer of Junior Theory Workshop and Northwestern QTW series Active in program committees for COLT , ICML , NeurIPS , and STOC conferences Teaching Portfolio : CS262: Mathematical Foundations of CS (Continuous Mathematics for Computer Science) CS212: Mathematical Foundations of Computer Science (multiple offerings since 2015) CS496: Graduate Algorithms (since 2016) CS396/496: Quantum Computation & Information (co-taught with S. Rao) CS497: Machine Learning Theory (Spring 2025 offering)

Piya PalView profile

Professor

• High Dimensional Statistical Signal Processing
• Compressive Sensing
• Tensor Methods
• +4 more

Prof. Piya Pal is a Professor in the Department of Electrical and Computer Engineering at the University of California, San Diego. Her research focuses on high-dimensional statistical signal processing, energy-efficient sampling techniques, and covariance-driven inference. She previously held an Assistant Professor position at the University of Maryland, College Park, and was affiliated with the Institute for Systems Research. Education: Ph.D. in Electrical Engineering from California Institute of Technology (2013). Notable achievements include the NSF CAREER Award (2016) and the 2014 Charles and Ellen Wilts Prize for her thesis on sparse sampling and estimation. Her work emphasizes structured sampling and robust algorithms for undersampled data analysis, with applications in sensor arrays, compressive sensing, and optical imaging. Research Interests: Energy-efficient sparse array design Correlation-aware sparse estimation Covariance compression and statistical inference Tensor methods in machine learning High-resolution imaging systems Publications highlight advancements in sparse array geometries (nested/coprime samplers), Cramér-Rao bound analysis, and hybrid beamforming. Recent work explores super-resolution imaging and millimeter-wave channel sensing with learned empirical priors. Her contributions address fundamental trade-offs between sample size, resolution, and domain knowledge integration. Scientific Awards: NSF CAREER Award (2016) 2014 Charles and Ellen Wilts Prize (Caltech) Advising & Grants: Current research is supported by NSF CAREER funding. Her lab focuses on interdisciplinary projects combining signal processing with medical imaging and wireless communication challenges.

Paul E. HandView profile

Associate Professor

• Machine Learning
• Artificial Intelligence
• Signal Processing
• +3 more

Paul E. Hand is an Associate Professor of Mathematics and Computer Science at Northeastern University, affiliated with both the College of Science and the Khoury College of Computer Sciences. He holds a Bachelor of Science in Applied and Computational Mathematics from the California Institute of Technology (2004) and a PhD in Mathematics from the Courant Institute at New York University (2009), where he received the Kurt O. Friedrichs Prize for outstanding dissertation. PhD in Mathematics, Courant Institute, NYU (2009) BS in Applied and Computational Mathematics, Caltech (2004) His research focuses on developing theoretical frameworks and algorithms for machine learning and artificial intelligence, particularly in signal recovery, phase retrieval, and vision/imaging. He also explores intersections of deep learning with convex optimization and has contributed to bilinear recovery problems. Recent publications emphasize generative models, inverse problems, and robust optimization techniques. Key themes include deep learning with provable recovery guarantees , convex programming for signal inversion , and manifold-based optimization . Kurt O. Friedrichs Prize for Outstanding Dissertation (2009) NSF CAREER Grant DMS-1848087 He has taught courses on Deep Learning, Machine Learning, and Signal Processing at Northeastern University since 2016, previously holding academic roles at Rice University (2016-2018) and MIT (2009-2016). He directs educational outreach initiatives and developed the educational resource Leading Lesson for multivariable calculus problem-solving.