جست‌وجوی استاد و پژوهشگر

Xinjie Lanمشاهده پروفایل

عضو هیئت علمی

• Machine Learning Theory
• eXplainable Artificial Intelligence (XAI)
• Computer Vision
• +۳ مورد دیگر

Xinjie Lan is an Assistant Teaching Professor at Rice University's Data to Knowledge (D2K) Lab. He joined in May 2022 and previously held an instructor position at the University of Delaware, where he earned his Ph.D. in Electrical and Computer Engineering. His research focuses on machine learning theory, eXplainable AI (XAI), computer vision, and data science applications. Lan teaches capstone courses and specialized data science techniques in Rice's Master’s of Data Science program, including statistical machine learning, computer vision, natural language processing, and deep learning. Dr. Lan has collaborated with industry, government agencies, and research institutes on over 20 projects addressing topics in social science, manufacturing, and biomedical engineering. His teaching philosophy emphasizes conceptual understanding of data science principles over mere technical proficiency, preparing students for the demands of the big data era. His research contributions span theoretical advancements in deep learning generalization, adversarial defense mechanisms, and probabilistic modeling of neural networks. He actively bridges theoretical insights with practical applications, particularly in interpretable AI and algorithmic robustness. Lab affiliations include the Rice Data to Knowledge Lab, where he leads applied data science initiatives. While no formal awards are listed, his extensive collaborative projects and pedagogical innovations reflect his commitment to interdisciplinary impact.

Arnab Bhattacharyyaمشاهده پروفایل

دانشیار

• Theoretical Computer Science
• Foundations of AI
• Algorithms for Big Data
• +۴ مورد دیگر

Arnab Bhattacharyya is an Associate Professor at the Department of Computer Science, University of Warwick. His research bridges the foundations of AI and theoretical computer science , focusing on algorithms for big data , high-dimensional statistics , and causal inference and discovery . He has co-taught courses at the University of Warwick, National University of Singapore, and Indian Institute of Science since 2013 Research Interests : Theoretical Computer Science , Foundations of AI , Algorithms , and Statistical Learning . His work includes property testing , causal graph estimation , and high-dimensional distribution learning . Scientific Awards : Best of PODS 2021 2022 ACM SIGMOD Research Highlight 2022 CACM Research Highlight Group Members : His former and current advisees include Palash Dey (IISc Ph.D., now at IIT Kharagpur), Suprovat Ghoshal (IISc Ph.D., now at University of Michigan), and Vipul Arora (NUS Ph.D., now at Simons Institute). Other notable students include Philips George John , Yuhao Wang , and Davin Choo .

• Machine Learning
• Artificial Intelligence
• Computational Biology
• +۳ مورد دیگر

Lennard Hilgendorf is a Researcher at the Department of Computer Science , University of Copenhagen . His work focuses on Machine Learning with applications in quantum computing, medical imaging, natural language processing, and environmental sustainability. Research Trends: His recent publications highlight interdisciplinary work at the intersection of quantum mechanics and machine learning, efficient AI architectures for environmental sustainability, explainable models for medical diagnostics, and multimodal approaches to ecological monitoring. Key keywords include Machine Learning , Quantum Computing , Medical AI , and Environmental Science . Labs & Collaborations: Affiliated with the SCIENCE AI Centre and the TreeSense Centre , which specialize in foundational machine learning research and remote sensing for global tree resources, respectively.

• Information Theory
• Coding Theory
• Communication Systems
• +۸ مورد دیگر

Ragnar Thobaben is a Professor in Communication Theory at the Division of Information Science and Engineering, part of the School of Electrical Engineering and Computer Science (EECS) at KTH Royal Institute of Technology. He has held this position since December 2006 and is affiliated with the CERCES Center for Resilient Critical Infrastructures. His research focuses on information and coding theory, with applications to secure communication systems, machine learning generalization, and DNA-based data storage. He has also contributed to data-driven decision tools for critical care medicine, such as in sepsis management. Education: Ragnar earned a Dipl.-Ing. (M.Sc.) in Electrical Engineering from Christian Albrechts University, Kiel, Germany in 2001, followed by a Dr.-Ing. (Ph.D.) in Electrical Engineering in 2007. His academic journey is complemented by extensive editorial roles, including Editor for IEEE Transactions on Communications (2016–2020) and IEEE Transactions on Information Forensics and Security (2020–2023). He has also served as Technical Program Committee member for major IEEE conferences like GLOBECOM, ICC, and PIMRC, and held organizational roles such as Publicity Chair for the 2011 IEEE Swedish Communication Technologies Workshop and Local-Arrangement Chair for the 2019 IEEE Information Theory Workshop. Research Interests: His work bridges theoretical and applied domains, emphasizing robustness and reliability in communication systems. Key topics include physical-layer security for critical infrastructures, information-theoretic PAC-Bayes bounds in machine learning, and microwave engineering innovations like glide symmetry in antenna design. He also explores interdisciplinary applications, such as data-driven tools for ICU patient monitoring and secure wireless power transfer. Advising & Grants: Thobaben has advised multiple PhD students, including current co-supervision of Martin Lindström (machine learning) and collaborations with Karolinska Institute on medical informatics projects (Anna Sundelin and Navid Korah Soltani under main supervisor Johan Mårtensson). His prior advisees span topics from generalization theory to secure relaying in cognitive networks. His recent publications (2024–2022) highlight advancements in PAC-Bayes bounds, sepsis clinical studies, and antenna engineering.

Emmanuel Candèsمشاهده پروفایل

استاد

• computational harmonic analysis
• statistics
• information theory
• +۱۲ مورد دیگر

Emmanuel Candès is the Barnum-Simons Chair in Mathematics and Statistics at Stanford University, where he is also a Professor of Statistics and, by courtesy, of Electrical Engineering. He is a member of the Institute of Computational and Mathematical Engineering at Stanford. Previously, he was the Ronald and Maxine Linde Professor of Applied and Computational Mathematics at the California Institute of Technology. His educational background includes: PhD in Statistics from Stanford University (1998) Diplome Ingenieur from Ecole Polytechnique (1993) Candès' research spans computational harmonic analysis, statistics, information theory, signal processing, and mathematical optimization with applications to imaging sciences, scientific computing, and inverse problems. His recent work focuses on conformal prediction, uncertainty quantification, and causal inference, with applications across diverse fields including genetics, machine learning, and artificial intelligence. He has made significant contributions to compressive sensing and mathematical signal processing. His recent publications demonstrate a strong focus on developing statistically rigorous methods for uncertainty quantification, particularly through conformal prediction frameworks. These works address challenges in high-dimensional statistics, machine learning validation, and causal inference across various application domains including genomics, natural language processing, and imaging sciences. His notable scientific achievements include: Alan T. Waterman Award from NSF IEEE Jack S. Kilby Signal Processing Medal (2021) Princess of Asturias Award for Technical and Scientific Research (2020) MacArthur Fellow (2017) Election to the National Academy of Sciences (2014) Election to the American Academy of Arts and Sciences (2014) Candès has served as Chair of the Statistics Department at Stanford (2016-2019) and is currently serving as Director of the Data Science Institute. His research has been supported by numerous grants from the National Science Foundation and other funding agencies. He has given over 60 plenary lectures at major international conferences across mathematics, statistics, biomedical imaging, and physics. As a leading researcher in mathematical statistics and computational mathematics, Candès maintains an active research group focusing on theoretical and applied aspects of statistical learning, signal processing, and optimization. His work bridges theoretical foundations with practical applications across scientific disciplines.

• Cyber-Physical Systems
• Runtime Verification
• Formal Methods
• +۵ مورد دیگر

Dejan Nickovic is a Professor affiliated with the Department of Cyber-Physical Systems at TU Wien. His research focuses on runtime verification, formal methods for cyber-physical systems (CPS), and software testing. He leads projects such as TAIGER (2023–2027) and ARTIST (2021–2026), advancing CPS safety and AI robustness. His work bridges theoretical formalisms with practical applications in robotics, IoT, and embedded systems. Key research themes include specification mining, fault localization, and automated verification. He has developed tools like DeepRIoT for robotic-IoT integration and FIM for Simulink fault analysis. His professorial dissertation (2020) formalized runtime verification techniques for CPS. Recent publications emphasize adaptive architectures, backdoor detection in AI, and hyperproperties for security. He collaborates extensively with academia and industry, addressing challenges in CPS testing and verification through grants like ZK 35-G (2019–2024). His lab supports platforms like CPS/IoT Ecosystem for research and education. Projects: TAIGER, ARTIST, EdgeAI, ProbInG Supervised students: N. Manjunath (PhD, 2021), Florian Exenberger (2019), Markus Heindl (2017)

Richard Zemelمشاهده پروفایل

استاد

• Machine Learning
• Unsupervised Learning
• Representation Learning
• +۵ مورد دیگر

Richard Zemel is a Professor in the Department of Computer Science at the University of Toronto, where he has been a faculty member since 2000. He holds the Google/NSERC Industrial Research Chair in Machine Learning and is a Canada CIFAR Artificial Intelligence Chair. His research focuses on foundational aspects of machine learning, including unsupervised learning, representation learning, few-shot learning, and ethical AI concerns like fairness and privacy. He co-founded SmartFinance, a financial tech startup, and developed the Toronto Paper Matching System used in major conferences like NIPS and ICML. Education: BSc in History & Science from Harvard University (1984), PhD in Computer Science from the University of Toronto (1993). Research Interests : Machine Learning, Unsupervised Learning, Probabilistic Models, Computer Vision, Natural Language Processing, Fairness in AI. Awards : NVIDIA Pioneers of AI Award Young Investigator Award (Office of Naval Research) Presidential Scholar Award NSERC Discovery Accelerator Supplements CIFAR Fellow Affiliations : Senior Fellow at Canadian Institute for Advanced Research (CIFAR), Co-Chief of Machine Learning at Rotman School of Business' Creative Destruction Lab, and Chief Scientist at Vector Institute for AI.

Debarghya Ghoshdastidarمشاهده پروفایل

استادیار

• Machine Learning
• Artificial Intelligence
• Network Science
• +۳ مورد دیگر

Prof. Debarghya Ghoshdastidar is an Assistant Professor of Theoretical Foundations of Artificial Intelligence at Technische Universität München (TUM) since 2019. He holds a Tenure Track position within the TUM School of Computation, Information and Technology. His research focuses on the statistical foundations of machine learning, network science, and their applications in neuroscience, crowdsourcing, and computer vision. Education: B.E. in Electrical Engineering from Jadavpur University (2010), M.S. and Ph.D. in Computer Science from Indian Institute of Science (2016). Following his PhD, he conducted postdoctoral research at the University of Tübingen, leading a Baden-Württemberg Foundation-funded junior research group. Research Interests: Theoretical machine learning, network analysis, statistical learning theory, and algorithmic guarantees for AI systems. His work bridges abstract theoretical frameworks with real-world applications, particularly in understanding the robustness and generalization of learning algorithms. Awards: Recipient of the Baden-Württemberg Elite Program for Postdocs (2017) and Google Ph.D. Fellowship (2013). His contributions include novel algorithms for graph hypothesis testing and spectral hypergraph partitioning. Grants and Advising: Led a junior research group in Tübingen; no explicit student lists provided here. Active in theoretical contributions to AI, with a focus on interpretable and robust machine learning.

Bulut Kuskonmazمشاهده پروفایل

پژوهشگر

• Cyber Security
• Control Systems
• Topological Data Analysis
• +۳ مورد دیگر

Bulut Kuskonmaz serves as a Researcher at Aalborg University's Department of Electronic Systems within The Technical Faculty of IT and Design. Based at Fredrik Bajers Vej 7C, 9220 Aalborg Øst, Denmark, he is affiliated with the Automation & Control Learning and Decisions Lab and maintains active research engagement since 2019. His research spans critical cyber-physical domains with emphasis on: Securing water distribution networks against cyber attacks using topological data analysis Developing secret sharing protocols for secure distributed machine learning Advancing information theory through mutual information and PAC-Bayesian frameworks Applying decentralized control to critical infrastructure systems Recent publications (2022-2024) reveal a cohesive trajectory integrating mathematical rigor with practical security solutions for cyber-physical systems, particularly in water network protection and cryptographic machine learning. He contributes to the SWIFT project (2019-2024) focused on electric power/water distribution systems, collaborating with researchers like R. Wisniewski and C.S. Kallesøe. His work demonstrates strong interdisciplinary connections between control theory, cryptography, and topological methods in security applications.

Yishay Mansourمشاهده پروفایل

استاد

• Machine Learning
• Reinforcement Learning
• Algorithmic Game Theory
• +۴ مورد دیگر

Yishay Mansour is a Professor of Computer Science at Tel Aviv University's School of Computer Science, where he has been a faculty member since 1992. He previously served as the first head of the Blavatnik School of Computer Science (2000-2002) and currently directs the Israeli Center of Research Excellence in Algorithms. He maintains a part-time research position at Google Research in Tel Aviv and has held previous positions at Microsoft Research in Israel. Professor Mansour received his PhD from MIT in 1990, followed by a postdoctoral fellowship at Harvard and a position as Research Staff Member at IBM T.J. Watson Research Center. His research spans several key areas including machine learning (particularly reinforcement learning and multi-armed bandits), algorithmic game theory, communication networks, and theoretical computer science. He has published over 100 journal papers and 200 conference proceedings, with recent work focusing on regret minimization, differential privacy, and reinforcement learning theory. His recent publications demonstrate a strong focus on theoretical foundations of machine learning, with particular emphasis on bandit algorithms, reinforcement learning, and game theory. The trends in his work show increasing integration of societal challenges like fairness and privacy into learning algorithms, alongside continued theoretical advances in optimization and learning guarantees. ACM Fellow (2014) ELLIS Fellow (2020) Asia-Pacific Artificial Intelligence Association Fellow (2022) AI Industry Alliance Fellow (2023) ERC Advanced Grant (2020) Multiple best paper awards including at COLT (2007), EC (2007), and EC (2025) Professor Mansour has supervised over a dozen doctoral students and numerous master's students, with his advisees working on topics ranging from reinforcement learning algorithms to algorithmic game theory and online learning. He has served on numerous program committees including as Program Chair for STOC (2016) and COLT (1998), and is currently an associate editor for several distinguished journals. His research has been supported by multiple grants from the Israel Science Foundation, ERC Advanced Grant, and other funding bodies. He leads the COLT-MDP lab which focuses on advancing the theory of reinforcement learning through three pillars: compact representation, efficient computation, and addressing societal challenges including fairness and privacy in learning algorithms.

• Mathematical Foundations of Machine Learning
• Explainable Artificial Intelligence
• Online Convex Optimization
• +۴ مورد دیگر

Tim van Erven is an Associate Professor of Machine Learning at the Korteweg-de Vries Institute for Mathematics within the Faculty of Science at the University of Amsterdam. His research focuses on the mathematical foundations of machine learning, with particular expertise in online convex optimization, statistical learning theory, and explainable AI. He leads a research group dedicated to developing mathematically rigorous machine learning methods that work effectively without manual fine-tuning. His research interests span the mathematical foundations of machine learning, with emphasis on explainable machine learning, adaptive methods in online convex optimization, faster-than-minimax rates for 'easy data' in statistical learning, PAC-Bayesian concentration inequalities, and statistical learning theory with frequentist analysis of Bayesian methods. His work bridges theoretical guarantees with practical applications, recently shifting toward formal mathematical analysis of explainability methods for black-box AI systems. His recent publications reveal a clear evolution from foundational work in online learning and statistical theory toward explainable AI, with increasing focus on theoretical guarantees for concept learning and algorithmic recourse. The publications demonstrate strong methodological rigor while addressing practical challenges in interpretability and robustness of machine learning systems. Scientific Awards: VICI grant by the Dutch Research Council (2025) VIDI grant by the Dutch Research Council (2019) TOP grant by the Dutch Research Council (2016) NIPS 2014 outstanding reviewer award Rubicon grant by the Dutch Research Council (2011) Van Erven serves in significant academic leadership roles including as a member of the board of directors for COLT, co-chair for the AI & Mathematics initiative, and organizer of the thematic seminar on machine learning. He has successfully secured multiple competitive research grants and leads a research group working on the Mathematical Foundations for Explainable AI project, with several PhD and Postdoc positions currently open.

• Artificial Intelligence
• Machine Learning
• Game Theory
• +۷ مورد دیگر

Frans A. Oliehoek is a Full Professor in Interactive Learning and Decision Making at the Department of Intelligent Systems, Delft University of Technology. He co-leads the Sequential Decision Making group and serves as director and co-founder of the ELLIS Delft Unit. His academic affiliations include senior membership at AAAI, board membership at IFAAMAS, and associate editor roles for JAIR and AIJ. His research focuses on interactive learning and decision making , integrating AI, machine learning, and game theory to develop algorithms for agents interacting in complex, dynamic environments. Key themes include Bayesian reinforcement learning , influence-based abstraction , multi-agent coordination , and uncertainty modeling in real-world applications like traffic control, human-AI collaboration, and e-commerce agents. Recent publications highlight advancements in Bayesian RL with factored POMDPs , multi-agent safety guarantees , and state abstraction . His work spans theoretical foundations (e.g., Nash equilibria, MDP homomorphic networks) and practical frameworks (e.g., SHARPIE for human-AI experiments). Scientific contributions include: ELLIS Fellowship Senior AAAI Membership Best Paper Award at ALA 2021 Outstanding Paper Award at RLC 2024 He has advised students like Miguel Suau and Robert Loftin, with applications in multi-agent reinforcement learning , Bayesian planning , and human-AI interaction . Collaborations span institutions like UC Berkeley, University of Amsterdam, and MIT.

Sutanu Gayenمشاهده پروفایل

استادیار

• Theory of Machine Learning
• Algorithms
• Bayesian Networks
• +۳ مورد دیگر

Sutanu Gayen is an Assistant Professor in the Department of Computer Science and Engineering at the Indian Institute of Technology Kanpur. His research focuses on theoretical aspects of machine learning, algorithms, and computational statistics. Designing algorithms for Bayesian networks and causality Complexity analysis of distribution learning Applications in high-dimensional statistical modeling His recent publications explore challenges in total variation distance computation, Gaussian tree models, and interventional distribution learning. Courses taught include advanced algorithms for machine learning and data structures. Research connects fundamental computational limits with practical statistical learning tasks.

Cameron Freerمشاهده پروفایل

پژوهشگر

• Probabilistic Computing
• Random Structures
• Mathematical Logic
• +۴ مورد دیگر

Cameron Freer is a Research Scientist at the Massachusetts Institute of Technology's Probabilistic Computing Project. His academic career spans multiple institutions including Keio University, Harvard University, and University of Hawaii at Manoa, with roles ranging from Postdoctoral Fellow to Project Associate Professor. Current affiliation: MIT Probabilistic Computing Project Past academic roles: Keio University SFC (2021–2024), MIT Brain and Cognitive Sciences (2013–2015), MIT Mathematics (2008–2010) Research interests focus on probabilistic computing , random structures , and their intersections with logic, mathematics, and artificial intelligence. Key contributions include foundational work on Markov categories , graphons , and feedback computability . Recent publications explore probabilistic programming systems , random graph modeling , and computable aspects of measure theory . Collaborators include prominent researchers from Harvard, Oxford, and MIT. Professional engagements include committee memberships in major conferences like POPL (2024), LAFI (2024–2025), and PLDI (2024). Holds PhD in Mathematics from Harvard University (2008).

Gergely Neuمشاهده پروفایل

عضو هیئت علمی

• Theoretical Machine Learning
• Reinforcement Learning Theory
• Online Optimization
• +۳ مورد دیگر

Gergely Neu is a Research Assistant Professor in the Department of Information and Communication Technologies (DTIC) at Universitat Pompeu Fabra in Barcelona, Spain. He leads a research group focused on theoretical aspects of sequential decision making and machine learning. Dr. Neu's research primarily centers on theoretical machine learning with a focus on: Reinforcement Learning Theory Online Optimization Bandit Problems Statistical Learning Theory Generalization Bounds Algorithms with provable performance guarantees His work emphasizes developing algorithms with strong theoretical guarantees in both computational and statistical complexity while maintaining practical implementability. Dr. Neu's research program seeks to bridge the gap between theoretical foundations and practical applications of machine learning systems, particularly in sequential decision-making contexts where performance guarantees are crucial. Analysis of Dr. Neu's recent publications reveals a strong focus on advancing the theoretical understanding of reinforcement learning, bandit algorithms, and generalization in machine learning. His work often employs techniques from convex analysis, information theory, and regret analysis to derive novel theoretical results with practical implications. A notable trend in his recent work is the exploration of offline reinforcement learning, contextual bandits, and the development of tighter generalization bounds using innovative analytical approaches that connect online learning with PAC-style guarantees. Dr. Neu has received numerous prestigious awards and recognitions for his research contributions: ERC Starting Grant (2020) Bosch AI Young Researcher Award (2020) Google Faculty Research Award (2019) "la Caixa" Junior Leader fellowship (2018) ELLIS Scholar appointment (2021) Outstanding Reviewer Award from ICML'16 Blue Ribbon for Outstanding Reviewing from IJCAI'16 Dr. Neu actively mentors several PhD students and postdoctoral researchers, fostering the next generation of theoretical machine learning researchers. His ERC Starting Grant provides substantial funding for his research program, enabling him to pursue ambitious theoretical investigations while training early-career researchers. He has successfully placed alumni in prestigious positions including assistant professorships at TU Delft and Politecnico di Milano. Dr. Neu's research group operates within the vibrant AI and Machine Learning research community at Universitat Pompeu Fabra, collaborating closely with other researchers in the Department of Information and Communication Technologies and maintaining strong ties with the Statistics group at the Department of Economics and Business. The group participates actively in the international machine learning theory community, regularly contributing to top conferences such as COLT, NeurIPS, ICML, and ALT, where Dr. Neu has served in leadership roles including Program Chair for COLT'23.