جست‌وجوی استاد و پژوهشگر

Thore Graepelمشاهده پروفایل

استاد

• Machine Learning
• Artificial Intelligence
• Multi-Agent Learning
• +۴ مورد دیگر

Thore Graepel is a Professor of Machine Learning at University College London (UCL) and Senior Vice President of Computational Science, AI & ML at Altos Labs. His research focuses on multi-agent learning systems, cooperative AI, and the application of machine learning to complex societal challenges. He obtained his PhD in machine learning from the Technical University of Berlin and has held positions at Microsoft Research and DeepMind. Notable contributions include the Xbox Live TrueSkill ranking system, the AdPredictor framework for Bing, and work on AlphaGo. Research Interests: Multi-agent learning, game theory, reinforcement learning, artificial intelligence ethics, and applications in cellular rejuvenation. Recent work emphasizes automatic curricula for deep multi-agent reinforcement learning and the social dynamics of AI systems. Education: PhD in Machine Learning (2001), Technical University of Berlin Affiliations: Chair of Machine Learning (part-time UCL), Senior Vice President at Altos Labs Key Projects: AlphaGo, TrueSkill ranking system, AdPredictor His TEDx talk ' The human pursuit of artificial intelligence ' discusses AI's potential to address global challenges while emphasizing responsible innovation. Teaching includes organizing UCL's Deep Learning Lecture Series with DeepMind researchers.

Nishant Mehtaمشاهده پروفایل

دانشیار

• Machine Learning Theory
• Online Learning
• Statistical Learning Theory
• +۶ مورد دیگر

Nishant Mehta is an Associate Professor in the Department of Computer Science at the University of Victoria, Canada. He serves as the Combined Program Advisor for Statistics/CSC. His research focuses on machine learning theory, including online learning, statistical learning theory, and reinforcement learning. He has held postdoctoral positions at CWI (Amsterdam) and ANU (Canberra), and earned his PhD from Georgia Tech (2013). Education: PhD in Computer Science (2013) and BS in Computer Science (2005), both from Georgia Institute of Technology. Research interests emphasize theoretically grounded methods in machine learning, including multi-armed bandits, PAC-Bayesian methods, and learning with self-interested agents. He has supervised multiple PhD and MSc students, including current advisees Quan Nguyen and Ali Mortazavi. Awards include the 2025 Best Reviewer Award for AISTATS and 2016 Outstanding Reviewer Award for NIPS. His work spans over 50 publications in top venues like NeurIPS, ICML, and COLT. He has held grants from NSERC and JPMorgan Chase, focusing on topics like representation learning and privacy-aware online learning. Teaching includes Machine Learning Theory, Data Mining, and Algorithms courses. He has been an Action Editor for TMLR and served as Area Chair for multiple conferences including NeurIPS and ICML.

Yuhao Baمشاهده پروفایل

استادیار

• Environmental Governance
• Public Policy Process
• Non-state Governance
• +۳ مورد دیگر

Yuhao Ba is an Assistant Professor at the Lee Kuan Yew School of Public Policy, National University of Singapore. His research focuses on non-state governance, environmental policy, and public policy processes. He holds a PhD in Public Administration from North Carolina State University. Research interests include corporate-led environmental governance, interactions between governance systems and policy processes, and sustainability outcomes. He is also committed to promoting equity and inclusion in public policy through his work with APPAM’s Equity & Inclusion fellowship. Education: PhD (Public Administration), North Carolina State University Office: 469C Bukit Timah Road, Singapore 259772 Email: yba@nus.edu.sg His recent work explores themes like policy innovation diffusion, climate change mitigation, and organizational performance evaluation. Publications span journals in public policy, environmental governance, and statistical methodologies. No grants or student advisement information is listed in the provided materials.

Mikael Skoglundمشاهده پروفایل

استاد

• Information theory
• Communications
• Signal processing
• +۵ مورد دیگر

Mikael Skoglund is a Professor and Head of the Division of Information Science and Engineering at KTH Royal Institute of Technology. His academic roles include membership in the Executive Committee of Digital Futures, and leadership in projects such as Humanizing the Sustainable Smart City (HiSSx) and PERCy. He holds a Ph.D. from Chalmers University of Technology (1997) and became a Professor at KTH in 2003. Education: Ph.D. in Signal Processing, Chalmers University of Technology, 1997 Docent in Signal Processing, KTH, 2001 Professor of Communication Theory, KTH, 2003 Research Interests: Focus on Information Theory, Communications, Signal Processing, Networks, Security and Privacy, Quantum Information, and Inference & Learning. His work bridges theoretical foundations with applications in wireless systems, federated learning, and privacy mechanisms. Projects & Collaborations: Leading initiatives in integrated sensing and communication (ISAC), federated learning, and smart city technologies. Active in strategic research areas like ICT-TNG and Digital Futures. Awards: IEEE Fellow (2023). Students & Grants: Supervised over 40 Ph.D. and postdoc researchers. Notable students include Borja Rodríguez Gálvez (Ph.D. 2024) and Amirreza Zamani (Ph.D. 2023). Active in securing grants for projects like PERCy and HiSSx. Labs/Teams: Part of the Digital Futures research center and the Division of Information Science and Engineering at KTH, fostering interdisciplinary innovation in digital technologies.

Rob Salomoneمشاهده پروفایل

پژوهشگر ارشد

• Statistics
• Machine Learning
• Computational Methods
• +۳ مورد دیگر

Dr. Rob Salomone is a Senior Research Fellow in Data Science at the Queensland University of Technology's (QUT) Centre for Data Science. He earned his Ph.D. in Statistics from the University of Queensland in 2018, focusing on advanced Monte Carlo methodology. Before joining QUT, he held research fellowships at the University of Queensland and UNSW Sydney. His research bridges statistics and machine learning, with an emphasis on developing robust computational techniques for large datasets and complex models. He specializes in creating scientific models that integrate advanced machine learning, domain expertise, and tailored computational methods to address intricate mathematical challenges. Salomone’s work spans Bayesian computation, Monte Carlo methods, and applications in computational biology and environmental systems. His contributions include advancements in nested sampling, CRISPR guide RNA optimization, and graph neural networks for anomaly detection. He also explores federated learning and uncertainty quantification in high-dimensional settings. Notable collaborations include work on agent-based tumor growth models and spectral subsampling for time series analysis. Though no formal students are listed, his research impact is evident through interdisciplinary projects and methodological innovations.

Hadi M. Dolatabadiمشاهده پروفایل

پژوهشگر ارشد

• Machine Learning
• Deep Learning
• Adversarial Robustness
• +۳ مورد دیگر

Hadi M. Dolatabadi is a Research Fellow in machine learning at the University of Melbourne node of the ARC Centre of Excellence for Automated Decision-Making & Society (ADM+S). He is affiliated with the School of Computing and Information Systems at the University of Melbourne, where he has nearly completed his Ph.D. focusing on robustness in deep learning. His research contributes to the ADM+S Centre's Machines Research Program, specifically developing algorithms for systematic treatment of bias and unfairness in AI systems. Hadi earned his Ph.D. from the School of Computing and Information Systems at the University of Melbourne, with his thesis examining current notions of robustness in neural networks and challenging them from novel perspectives. His doctoral research bridges theoretical foundations with practical applications in machine learning. Hadi's research interests center on machine learning with a strong emphasis on robustness and fairness. He specializes in adversarial robustness, coreset selection, and generative modeling techniques including normalizing flows, GANs, and diffusion models. His approach uniquely combines statistical perspectives with generative modeling frameworks to address fundamental challenges in AI. His work has significant implications for developing more reliable and equitable automated decision-making systems, particularly in contexts where bias and unfairness could have serious societal consequences. Analysis of Hadi's publication record reveals a strong focus on the intersection of theoretical machine learning and practical AI ethics. His work consistently addresses the tension between model performance and robustness, while increasingly incorporating fairness considerations. The progression of his research shows a movement from foundational robustness questions toward more applied problems related to bias detection and mitigation in real-world AI systems. His publications span top-tier AI conferences including NeurIPS, ECCV, and AISTATS, demonstrating both technical depth and relevance to contemporary AI challenges. Hadi completed a six-month research internship at Amazon Science during his Ph.D. studies, gaining valuable industry experience while maintaining strong academic research output. His technical expertise spans both theoretical aspects of machine learning and practical implementation of complex algorithms. While specific grants aren't mentioned in the available information, his position at the ARC Centre of Excellence indicates involvement in significant collaborative research funding. As part of the ADM+S Centre's Machines Research Program, Hadi contributes to a multidisciplinary team addressing challenges in automated decision-making. The Centre brings together researchers from humanities, social sciences, and technological fields to create knowledge and strategies for responsible, ethical, and inclusive automated decision-making systems. Hadi's technical expertise in machine learning provides crucial foundation for the Centre's work on bias and fairness in AI systems.

Oleg Sokolskyمشاهده پروفایل

استاد پژوهشی

• Cyber-Physical Systems
• Formal Verification
• Runtime Monitoring
• +۲ مورد دیگر

Research Professor at University of Pennsylvania leading projects on cyber-physical systems safety. Directs DARPA-funded research in assured autonomy and attack-resilient control systems. Education: PhD in Computer Science from SUNY Stony Brook (1996). Research: Develops formal methods for runtime monitoring and verification of embedded systems. Current projects include medical device interoperability and physiological closed-loop control. Created MaC runtime verification framework and contributed to AADL standardization. Teaching: Advises PhD students in real-time systems and formal verification. Teaches courses on mathematical foundations of computer security. Awards: Best Paper, IEEE/ACM CPS Week (2014) Best Student Paper, RTAS (2012) Labs & Projects: Member of PRECISE Center. Leads DARPA projects on assured autonomy and SPARCS. Collaborates with FDA on medical device safety frameworks.

Umut Simsekliمشاهده پروفایل

پژوهشگر

• Mathematical Machine Learning
• Markov Chain Monte Carlo
• Deep Learning Theory
• +۴ مورد دیگر

Umut Simsekli is a Researcher at INRIA - SIERRA team and École Normale Supérieure de Paris, Computer Science Department. He earned his PhD (2015) and MSc (2010) from Boğaziçi University, and a BSc from Sabancı University (2008). His career includes roles at Télécom Paris (2016-2020) and visiting positions at Oxford and Boğaziçi University. Research Focus: Mathematical Machine Learning, emphasizing Deep Learning theory, Heavy-Tailed Optimization, Bayesian Inference, and Stochastic Dynamics. Grants: Principal Investigator for ERC Starting Grant DYNASTY (€1.5M, 2022-2027) and co-PI for ANR/TUBITAK grant FBIMATRIX (2016-2022). Recent Article Trends: Explores PAC-Bayesian generalization, heavy-tailed SGD dynamics, and topological stability in optimization algorithms. Scientific Awards: ERC Starting Grant (2021) ICASSP Best Student Paper Award (2020) Multiple IEEE/SPS Student Travel Grants (2012-2020) Victor L. Wooten Bass/Nature Camp Scholarship (2005) Teaching & Advising: Teaches Deep Learning at École Polytechnique and previously led courses on Probabilistic Graphical Models at Télécom Paris. Supervises PhD students Dario Shariatian, Benjamin Dupuis, and others.

• Weak Dependence
• Limit Theorems for Stochastic Processes
• Statistical Inference for Mixed Moving Average and Ambit Fields
• +۴ مورد دیگر

Dr. Imma Valentina Curato is a researcher specializing in probability theory, financial econometrics, and stochastic processes. She holds a DFG-funded research grant focused on PAC Bayesian bounds for light cone and trajectory data, with a particular emphasis on high-frequency financial modeling and statistical inference for complex random fields. Education: PhD in Mathematics, University of Pisa (2013) MSc in Mathematics, University of Florence (2009) BSc in Mathematics, University of Florence (2006) Research Focus: Weak dependence in stochastic processes Limit theorems for spatio-temporal models Fourier and Laplace transform methods for volatility estimation Bayesian learning in ambit field models Notable Contributions: Developed Fourier-based analysis for stochastic leverage effects Advanced central limit theorems for mixed moving averages Created nonparametric volatility estimation techniques Scientific Recognition: DFG Research Grant recipient Published in top-tier journals like Annals of Applied Probability and Quantitative Finance Academic Engagement: Regular participant in international conferences (SPA, European Meeting of Statisticians, AMASES) Invited speaker at institutions like University of Florence, Imperial College London, and Aarhus University Educational Leadership: Teaches courses on statistical learning, financial engineering, and stochastic processes Organizes seminars on Gaussian processes and high-frequency econometrics

Badr-Eddine Chérief-Abdellatifمشاهده پروفایل

پژوهشگر

• Mathematical Statistics
• Machine Learning Theory
• Generalized Bayesian Inference
• +۶ مورد دیگر

Badr-Eddine Chérief-Abdellatif is a CNRS Researcher at Sorbonne Université , affiliated with the Laboratoire de Probabilités, Statistique et Modélisation (LPSM) . His research spans mathematical statistics and machine learning theory , focusing on generalized Bayesian inference , robustness , and variational inference . He previously held a postdoctoral position at the University of Oxford and earned his PhD in 2020 from Institut Polytechnique de Paris under Pierre Alquier. His work addresses robust statistical methods using Maximum Mean Discrepancy (MMD) , PAC-Bayesian theory , and kernel techniques . Recent publications explore meta-learning , VAE reconstruction guarantees , and missing data analysis . He received the Best Student Paper Award at AISTATS 2022 and a Best Paper Award at ACML 2019. Chérief-Abdellatif contributes to online learning , copula estimation , and sparse deep learning . His theoretical results on variational inference have been published in top venues like NeurIPS , JASA , and JMLR . He also co-invented a patent for proportions determination in biological ensembles (2024). Scientific Awards : Best Student Paper Award, AISTATS 2022 Best Paper Award, ACML 2019 Travel Award for Academic Conferences

Tamir Hazanمشاهده پروفایل

دانشیار

• Machine Learning
• Theoretical Machine Learning
• Computer Vision
• +۶ مورد دیگر

Associate Professor Tamir Hazan is a faculty member at Technion - Israel Institute of Technology, where he joined in 2015. His research focuses on theoretical and practical aspects of machine learning, with applications spanning computer vision, natural language processing, and computational biology. His work bridges mathematical foundations with real-world problem solving in complex systems. Professor Hazan received his Ph.D. from the Hebrew University in 2009. His academic trajectory has established him as a leading researcher in machine learning theory and its applications, with a particular emphasis on developing mathematically rigorous approaches to modern AI challenges. Professor Hazan's research centers on mathematically founded solutions to problems demonstrating non-traditional statistical behavior. His work encompasses perturbation models for efficient learning of high-dimensional statistics, deep learning of infinite networks, and primal-dual optimization for high-dimensional inference problems. His research program spans three major interconnected areas: attention models that improve prediction interpretability, perturbation frameworks that integrate optimization and sampling through extreme value statistics, and convex duality approaches to message-passing in graphical models. His work demonstrates both theoretical depth and practical relevance across multiple domains. Analysis of Professor Hazan's recent publications reveals an evolving research trajectory with increasing emphasis on interpretable machine learning, causal modeling, and applications in medical imaging and behavioral science. His work consistently bridges theoretical foundations with practical implementations, with recent publications showing strong connections between perturbation theory, attention mechanisms, and optimization frameworks. The interdisciplinary nature of his research is evident in applications ranging from pedestrian navigation using smartphone sensors to video-text matching systems and medical image analysis. Professor Hazan has mentored numerous students throughout his career, including: Alex Schwing, now Assistant Professor at UIUC Alon Cohen, now Associate Professor at Tel Aviv University Idan Schwartz, currently Postdoc at Tel Aviv University Current Ph.D. students: Guy Lorberbom, Itai Gat, and Hedda Cohen Multiple M.Sc. students including Adi Manos, Ram Yazdi, and others Professor Hazan's research group maintains an active program with several key focus areas: Attention models for interpretable and improved prediction processes in visual question answering and multimodal applications Perturbation models that enable efficient statistical reasoning in complex systems with exponential configuration spaces Markov random fields, convex duality, and message-passing algorithms for structured prediction and distributed computing

Luiz Chamonمشاهده پروفایل

استادیار

• Machine Learning
• Reinforcement Learning
• Constrained Optimization
• +۳ مورد دیگر

Luiz Chamon is an Assistant Professor (tenure-track) and Hi!PARIS Chair holder at the Center for Applied Mathematics (CMAP) , École polytechnique, Paris, France. His research bridges machine learning with control theory and signal processing, focusing on intelligent systems that extract, process, and act on information under constraints. Research Interests: He specializes in constrained learning frameworks for machine learning, with applications to reinforcement learning, statistical signal processing, and optimization. His work includes adversarial robustness, safe policy design, and duality analysis in constrained settings. Article Trends: Recent publications span differential equation solving (ICLR 2025), primal-dual sampling (NeurIPS 2024), and resilient reinforcement learning (IEEE Trans. Autom. Control 2024). Common themes include constrained optimization, robustness, and bridging theory with practical applications in wireless systems and graph signal processing. Scientific Awards: Hi!PARIS Chair (2025) ELLIS Scholar (2025) Best Student Paper Award (ICASSP 2020) Best Paper Award (ICASSP 2020) Top 50 Most Accessed Articles in IEEE TSP (2019) Grants & Projects: Currently leads a 4-year ANR JCJC project on "Beyond (Robust) Learning: Striking Compromises in Machine Learning" (2024). Previously involved in technical reports on aircraft vibroacoustics and wireless power systems. Labs & Teams: Heads a research group at École polytechnique developing tools for constrained learning, collaborating with institutions like University of Pennsylvania and IMPRS-IS. Organizes tutorials and panels on constrained learning and career development.

• Machine Learning
• Support Vector Machines
• Evolution Strategies
• +۴ مورد دیگر

Christian Igel is a Full Professor at the Department of Computer Science (DIKU), University of Copenhagen. He serves as Director of the SCIENCE AI Centre and co-lead of the Pioneer Centre for Artificial Intelligence. Igel holds a Doctoral degree from Bielefeld University (2002) and a Habilitation from Ruhr-University Bochum (2010). Previously, he was a Juniorprofessor at Ruhr-University Bochum (2003-2010). His research focuses on fundamental and applied machine learning, including: kernel methods, evolutionary optimization, deep neural networks, PAC-Bayesian analysis, and applications supporting sustainable development goals. He maintains extensive collaborations across disciplines, particularly in environmental monitoring and medical informatics. Igel's recent publications demonstrate strong interdisciplinary focus with applications in: Environmental science (tree cover mapping, carbon stock quantification) Healthcare (sleep staging, mental health epidemiology) Core ML theory (monotonic networks, PAC-Bayesian bounds) His work consistently appears in high-impact venues including Nature, ICML, and NeurIPS. Awards and Honors: ELLIS Fellow (European Lab for Learning and Intelligent Systems) Editorial Roles: Editor, German Journal on Artificial Intelligence (KI) Associate Editor, Evolutionary Computation Journal (ECJ) Associate Editor, Artificial Intelligence Journal (AIJ)

Amaury Habrardمشاهده پروفایل

استاد

• Machine Learning
• Metric and Similarity Learning
• Domain Adaptation
• +۶ مورد دیگر

Amaury Habrard is a Full Professor in Computer Science at Jean Monnet University (UJM) , Saint-Etienne, and a member of the Laboratoire Hubert Curien UMR CNRS 5516 . He leads the Data Intelligence Research Group and manages the international Machine Learning and Data Mining (MLMD) Master’s Program . PhD in 2004 at UJM Habilitation thesis in 2010 at Aix-Marseille University Assistant Professor at Aix-Marseille University (2005–2011) His research focuses on Machine Learning , with key interests in Metric and Similarity Learning , Domain Adaptation and Transfer Learning , Learning Theory , Fraud and Anomaly Detection , and Grammatical Inference . He co-authored a book on Metric Learning (Morgan & Claypool, 2015) and another on Domain Adaptation Theory (ISTE, 2019). His work explores theoretical foundations (e.g., PAC-Bayesian bounds, spectral learning) and practical applications (e.g., melody recognition, image classification, side-channel attacks). Recent publications highlight advancements in metric learning (robustness, structured data), domain adaptation (unsupervised methods, theoretical guarantees), and machine learning theory (concentration bounds, majority votes). Scientific Awards : ICTAI'11 Best Paper Award NeurIPS'21 Reviewer Award ICML'19 Top Reviewer Award NeurIPS'18 Reviewer Award IJCAI'18 Senior PC Award ICML'18 Top Reviewer Award Advising : Supervised PhD students including Julien Tissier (Binary Representation Learning), Jordan Frery (Ensemble Methods for Fraud Detection), Guillaume Metzler (Outlier Detection in Bank Fraud), Michael Perrot (Metric Learning), Mattias Gybels (Spectral Learning), Jean-Philippe Peyrache (Unsupervised Domain Adaptation), Emilie Morvant (PAC-Bayesian Domain Adaptation), Aurélien Bellet (Metric Learning with Generalization Guarantees), and Laurent Boyer (Probabilistic Edit Similarities). Labs/Teams : Leads the Data Intelligence Research Group and is part of the new Inria MALICE project-team on Physics-informed Machine Learning. Collaborated with the PASCAL2 Network of Excellence and European Marmota Project .

• Machine Learning
• Bayesian Nonparametrics
• Statistical Theory
• +۳ مورد دیگر

Peter Orbanz is a Professor of Machine Learning at the Gatsby Computational Neuroscience Unit, University College London (UCL). He previously held roles as Assistant and Associate Professor in the Department of Statistics at Columbia University, and completed postdoctoral research at the University of Cambridge under Zoubin Ghahramani. His research focuses on machine learning, Bayesian nonparametrics, symmetry in statistical models, and dynamics. He has spent sabbaticals at the Isaac Newton Institute, Microsoft Research New England, and UC Berkeley. Orbanz earned his PhD in 2008 from ETH Zurich under Joachim M. Buhmann, with a thesis on Bayesian nonparametric models. His work bridges theoretical foundations of machine learning with practical applications, emphasizing symmetry properties and scalable inference methods. Current research includes causal uncertainty quantification, Gaussian process dynamics, and equivariant neural networks. He teaches advanced courses on probabilistic learning, Bayesian nonparametrics, and statistical theory at UCL and Columbia. His research group at UCL includes PhD students Hugh Dance, Kevin H. Huang, Vasco Portilheiro, and Vince Velkey. Former advisees include Morgane Austern (Harvard), Benjamin Bloem-Reddy (UBC), and Victor Veitch (Chicago). Orbanz has authored influential papers on topics such as exchangeable random structures, Gaussian universality, and scalable MCMC methods. His work often integrates concepts from probability theory, statistical physics, and computational neuroscience. He maintains active collaborations with institutions worldwide and contributes to open-source tools for Bayesian modeling.