جست‌وجوی استاد و پژوهشگر

Nima Akbarzadehمشاهده پروفایل

پژوهشگر ارشد

• Game theory
• Optimal order
• Mathematical modeling
• +۳ مورد دیگر

Nima Akbarzadeh is a Research Fellow at HEC Montréal since May 2023, co-supervised by Erick Delage and Yossiri Adulyasak. He previously completed his Doctorate (2017–2022) in Electrical and Computer Engineering at McGill University under Aditya Mahajan's supervision. Current affiliation: HEC Montréal (Postdoctoral Research Fellow) PhD: McGill University (Electrical and Computer Engineering) Research focus areas: Game theory, Mathematical modeling, and Optimization without derivatives Nima's work bridges algorithm development with risk-aware reinforcement learning (RL), particularly in restless multi-arm bandits and weakly coupled Markov decision processes (MDPs). His recent publications at AISTATS 2025 highlight advancements in sequential decision-making frameworks and fair resource allocation strategies. Scientific awards include: 2024 GERAD Postdoctoral Fellowship 2020–2022 FRQNT Doctoral Scholarship 2017–2019 McGill Engineering Doctoral Award He actively participates in academic workshops and seminars, including IVADO's Risk-Aware/Safe RL Workshop (2023) and McGill's Informal Systems Theory Seminar (2021).

Eric Laberمشاهده پروفایل

استاد

• Statistical Reinforcement Learning
• Precision Medicine
• Dynamic Treatment Regimes
• +۳ مورد دیگر

Eric Laber serves as James B. Duke Distinguished Professor of Statistical Science at Duke University, with cross-appointments as Professor of Biostatistics & Bioinformatics in the School of Medicine and Research Professor of Global Health. He co-directs the Duke Computing Initiative and maintains active roles in the Department of Statistical Science. His educational background includes: Ph.D. in Statistics, University of Michigan, Ann Arbor (2011) M.A. in Statistics, University of Michigan, Ann Arbor (2007) Laber's research pioneers statistical reinforcement learning for dynamic decision-making in complex health environments. He specializes in developing methodologies for Sequential Multiple Assignment Randomized Trials (SMARTs) to optimize personalized treatment sequences in precision medicine. His work bridges machine learning with clinical applications, focusing on cancer therapeutics, mental health interventions, and resource-constrained global health settings. Recent innovations address network interference in policy learning and risk-sensitive optimization for digital health platforms. Analysis of his 15 most recent publications reveals strong trends in adaptive clinical trial design, with increasing emphasis on mHealth applications (40% of recent work), PTSD management in cancer survivors (25%), and network-based reinforcement learning (20%). Key methodological threads include Thompson sampling variants (33%), functional data analysis for truncated outcomes (15%), and causal inference under interference (25%). His scientific recognition includes: James B. Duke Distinguished Professorship (premier faculty honor at Duke) Laber secures substantial grant funding for high-impact health research, currently leading 10 active projects totaling over $15M. Major awards include NIH/NCI funding for next-generation SMARTs in cancer therapeutics (2023-2028), NSF support for risk-sensitive statistical learning (2024-2027), and multiple NIH trials for digital mental health interventions. His collaborative approach spans oncology, psychiatry, and global health teams, with special focus on vulnerable populations including cancer survivors and adolescents. As Co-Director of the Duke Computing Initiative, he leads interdisciplinary teams developing scalable computational frameworks for precision medicine. Current efforts integrate reinforcement learning with electronic health records systems to create real-time clinical decision support tools, particularly for resource-limited settings in infectious disease management and chronic pain treatment.

• Communication Networks
• Decentralized Algorithms
• Large Deviations
• +۵ مورد دیگر

Ayalvadi Ganesh is a Lecturer in the Department of Mathematics at the University of Bristol's School of Mathematics, where he teaches advanced courses including Complex Networks, Stochastic Optimisation, and Queueing Networks. His academic work bridges theoretical mathematics with practical network applications. His research spans communication networks , decentralized algorithms , and stochastic modeling , with core expertise in large deviations theory , random graphs , queueing systems , and information theory . Recent work demonstrates strong focus on multi-agent bandit problems, epidemic modeling on networks, and latency optimization in distributed systems, reflecting interdisciplinary applications from cybersecurity to biological networks. Analysis of his 15 most recent publications reveals dominant trends in decentralized decision-making (38% of works), network epidemics/rumor spreading (27%), and stochastic optimization (20%), with increasing crossover into machine learning and biological applications since 2020. Best Paper award at ACM SIGMETRICS 2010 for 'Load balancing via random local search in closed and open systems' His teaching portfolio includes graduate-level courses on Complex Networks, Stochastic Optimisation, and Queueing Theory, with documented emphasis on connecting theoretical foundations to real-world network challenges. While specific grant details aren't provided in source materials, his publication pattern suggests sustained research funding in network science and stochastic systems.

Romeil Singh Sandhuمشاهده پروفایل

استادیار

• Computer Vision
• Machine Learning
• Network Science
• +۴ مورد دیگر

Romeil Singh Sandhu serves as Assistant Professor in Biomedical Informatics at Stony Brook University with adjunct appointments in Computer Science and Applied Mathematics & Statistics, directing the Laboratory for Imaging, Networks, and Control (LINC) from the Health Sciences Center. His academic credentials include: B.S. from Georgia Institute of Technology (2006) M.S. from Georgia Institute of Technology (2009) Ph.D. from Georgia Institute of Technology (2010) Dr. Sandhu's research integrates geometry, statistics, and control theory to advance computer vision (3D reconstruction, satellite pose estimation), network science (hypergraph dynamics, Ricci curvature), and systems biology (protein interaction networks, cellular robustness). His methodological innovations span level-set methods, variational techniques, and curvature-based network analysis with applications in medical imaging and aerospace systems. Analysis of his 2019-2023 publications reveals three dominant trajectories: (1) geometric network analysis using Ricci curvature to quantify biological network fragility; (2) distributed reinforcement learning with communication-efficient multi-agent actor-critic frameworks; and (3) medical/satellite image reconstruction via radar-based variational methods and active surfaces. These threads consistently leverage differential geometry to solve inverse problems in complex systems. The Laboratory for Imaging, Networks, and Control (LINC) develops computational frameworks bridging theoretical mathematics with healthcare and aerospace applications, particularly focusing on shape analysis, network dynamics, and control systems for medical diagnostics and satellite imaging.

• Machine Learning Theory
• Foundations of Artificial Intelligence
• Operations Research
• +۵ مورد دیگر

Yunzong Xu is an Assistant Professor in the Department of Industrial and Enterprise Systems Engineering (ISE) and Coordinated Science Laboratory (CSL) at the University of Illinois at Urbana-Champaign, with affiliations in the Departments of Computer Science (CS) and Electrical and Computer Engineering (ECE). He holds a Ph.D. in Data, Systems, and Society from MIT (2023) and dual B.S. degrees from Tsinghua University in Economics and Mathematical Sciences (2018). His research focuses on machine learning theory , foundations of AI , operations research , and management science , with specific interests in online learning , deep learning , sequential decision making , and mathematical problems related to markets , incentives , and social good . His work bridges theoretical analysis with applications in dynamic pricing, reinforcement learning, and network revenue management. Recent publications highlight algorithmic complexity in contextual bandits, offline reinforcement learning , and phase transitions in constrained bandit problems. His research has been recognized by awards from INFORMS, Applied Probability Society, and IBM Service Science. Honorable Mention, INFORMS George Nicholson Student Paper Competition (2020) Winner, INFORMS Data Mining Best Theoretical Paper Award (2020) Finalist, Applied Probability Society Best Student Paper Award (2019) Finalist, INFORMS Undergraduate Operations Research Prize (2018) Finalist, IBM Service Science Best Student Paper Award (2021) He teaches graduate courses on Foundations of Modern Machine Learning (IE598) and undergraduate courses in optimization models (IE310). For more information, visit his personal homepage .

Aleida Braaksmaمشاهده پروفایل

مدرس

• Artificial Intelligence
• Health and Well-being
• Reinforcement Learning
• +۷ مورد دیگر

Aleida Braaksma is a Lecturer at the University of Twente, affiliated with the TechMed Centre and Mathematics of Operations Research department. Her work bridges Artificial Intelligence with Health and Well-being , focusing on optimizing healthcare systems through Operations Research methodologies. Key Affiliations: Digital Society Institute, TechMed Centre, Mathematics of Operations Research department Research Themes: Reinforcement Learning, Data Mining, Process Mining, and Queueing Theory applications in healthcare logistics Her recent publications highlight advancements in medical diagnostic scheduling , bed allocation , and adaptive clinical trial designs . She has pioneered dynamic robust optimization frameworks for time-sensitive pharmaceutical workflows and developed sampling-based methods for Gittins index approximation in stochastic environments. Scientific contributions include: Optimization of rheumatology outpatient clinics via patient classification algorithms Response-adaptive procedures in clinical trials using constrained Markov decision processes Real-time forecasting systems for pandemic-related hospital capacity planning Computerized decision support for nurse-to-patient assignment

Weina Wangمشاهده پروفایل

استادیار

• Applied Probability
• Stochastic Systems
• Reinforcement Learning
• +۷ مورد دیگر

Weina Wang is an Assistant Professor in the Computer Science Department at Carnegie Mellon University, joining in Fall 2018. Her research lies at the intersection of applied probability , stochastic systems , and reinforcement learning , focusing on decision-making in large-scale systems with applications to computing resource orchestration, data privacy, and graph statistics. She has received prestigious awards including the NSF CAREER Award (2022) , ACM MobiHoc Best Paper (2022) , and ACM SIGMETRICS Rising Star Research Award (2023) . PhD in Electrical Engineering, Arizona State University (2016) Bachelor’s in Electronic Engineering, Tsinghua University (2009) Her recent publications span restless bandits , queueing theory , and attributed graph alignment , reflecting her dual focus on fundamental limits and algorithmic solutions. Notable collaborations include work on privacy-preserving data routing , phase-aware scheduling , and erasure-coded servers for heterogeneous traffic. She has advised PhD students Jalani Williams , Tuhinangshu Choudhury , and Yige Hong . Her research has been recognized with best paper awards and grants like the NSF CAREER . She also contributes to professional societies, recently joining the INFORMS Applied Probability Society council . Her teaching includes courses like Probability and Computing and Fundamentals of MDPs and Reinforcement Learning .

• Causal Machine Learning
• Mechanistic Machine Learning
• Dynamical Systems
• +۶ مورد دیگر

Niki Kilbertus is a Professor in the Department of Informatics at the Technical University of Munich and a group leader at Helmholtz AI (Helmholtz Munich). They are also affiliated with MCML, the Konrad Zuse School relAI, and the Munich Unit of ELLIS. Since 2024, they have been a member of the Junge Akademie and received the Leopoldina Prize for Young Scientists. In 2025, they were awarded an ERC Starting Grant and achieved tenure at TUM. Professor Kilbertus's research focuses on causal machine learning, mechanistic ML, dynamical systems, and AI for science. Their work spans theoretical foundations of causal inference and practical applications across scientific domains. They have made significant contributions to causal effect estimation, causal discovery in stochastic processes, learning differential equations, and fair machine learning. Their research often bridges computer science with physics, biology, and climate science, demonstrating the interdisciplinary nature of their work. Professor Kilbertus has published extensively in top machine learning venues including NeurIPS, ICML, and ICLR, with numerous publications in 2024-2025. Their recent work shows a strong trend toward causal discovery in continuous-time systems, intervention modeling, and physics-informed machine learning applications. Scientific Awards: Leopoldina Prize for Young Scientists (2024) ERC Starting Grant (2025) Professor Kilbertus actively supervises multiple PhD students and collaborates with researchers across institutions including Max Planck Institutes and Helmholtz centers. They serve as an Action Editor for TMLR and regularly review for major ML conferences. The research group is well-funded through the ERC grant and institutional support from TUM and Helmholtz AI, enabling active recruitment of new PhD students and postdocs. Based at Technical University of Munich and Helmholtz AI, Professor Kilbertus's team works at the intersection of theoretical machine learning and scientific applications, with particular strengths in causal reasoning for complex dynamical systems.

Chevaleyre Yannمشاهده پروفایل

استاد

• Artificial Intelligence
• Multi-Agent Systems
• Computational Social Choice
• +۳ مورد دیگر

Chevaleyre Yann is a Professor of Computer Science at LAMSADE, Paris-Dauphine PSL University, where he has been working since 2017. Previously, he served as Professor of Computer Science at Paris-Nord University from 2009 to 2017 and as Director of the "data science" team at the LIPN laboratory. His academic journey includes a Lecturer position at LAMSADE, Paris-Dauphine University from 2002 to 2009, a Habilitation thesis at Paris-Dauphine University in 2009, and a Doctorate at Pierre and Marie Curie University under the supervision of Jean-Daniel Zucker from 1998 to 2001. Professor Chevaleyre's research spans multiple areas within artificial intelligence and computer science, with particular expertise in multi-agent systems, computational social choice, and machine learning. His work on preference modeling, voting theory, and resource allocation has significantly contributed to the field of computational social choice. More recently, his research has expanded into adversarial machine learning, robust classification, and generative models, reflecting the evolving landscape of AI research. His publication record demonstrates consistent contributions across multiple domains, with recent work focusing on precision-recall optimization in generative models, the role of randomization in adversarial robustness, and novel approaches to graphical bilinear bandits. His research shows a clear trajectory from foundational work in multi-agent systems toward more contemporary challenges in machine learning security and evaluation. Professor Chevaleyre has maintained active collaborations with researchers across France and internationally, evidenced by his extensive co-authorship network. His work bridges theoretical computer science with practical applications in areas ranging from robotics to bioinformatics.

• Computer Vision
• Machine Learning
• Adversarial Robustness
• +۴ مورد دیگر

Jenny Schmalfuss is a Doctoral Researcher at the Institute for Visualization and Interactive Systems (VIS) within the Faculty of Computer Science, Electrical Engineering, and Information Technology at the University of Stuttgart. She is also a scholar of the International Max Planck Research School for Intelligent Systems (IMPRS-IS). Her research focuses on computer vision and machine learning, specifically investigating robustness of deep learning methods against distribution shifts and adversarial attacks. Her primary research interests include computer vision, machine learning, and the intersection of these fields with robustness analysis. She has made significant contributions to understanding weaknesses in vision language models and motion estimation techniques like optical flow. Her work explores how to quantify and improve model robustness through adversarial testing frameworks. Her publication record shows a strong focus on adversarial robustness in motion estimation, with multiple papers at top-tier conferences including CVPR, ICCV, and ECCV. Recent work includes the PARC framework for analyzing vision language models (CVPR 2025), Distracting Downpour for weather-based adversarial attacks (ICCV 2023), and foundational work on adversarial snow attacks (ECCV AROW 2022). Poster Award at ICVSS 2023 Best Paper Award at ECCV AROW Workshop 2022 Best SimTech Bachelor's thesis 2021 (supervised) Jenny actively supervises numerous Master's theses, Bachelor's theses, and research projects annually, focusing primarily on optical flow robustness, adversarial attacks, and motion estimation. She has also completed an internship with NVIDIA's Autonomous Vehicle Perception Research Group in Santa Clara, CA, USA from April to November 2024, and previously worked as a research intern at the National University of Singapore and University of Houston. She teaches regularly in the Computer Vision and Intelligent Systems program, organizing colloquia and supervising seminars on Recent Advances in Computer Vision since 2021. Her teaching portfolio includes coordinating tutorials for Computer Vision and Imaging Science courses.

Yang Liمشاهده پروفایل

دانشیار

• Statistical Machine Learning
• Bayesian Nonparametrics
• Scalable Optimization
• +۵ مورد دیگر

Yang Li serves as Associate Professor of Marketing and Associate Dean for the MBA Program at Cheung Kong Graduate School of Business (CKGSB). Holding a PhD in Marketing from Columbia Business School alongside dual master's and bachelor's degrees from Columbia and Peking University respectively, he bridges advanced statistical methodologies with practical business applications. His research centers on statistical machine learning and Bayesian nonparametrics applied to consumer behavior analysis, with specialization in online personalization, text mining, and choice modeling. Recent work demonstrates significant focus on fragmented attention economies, ethical AI frameworks, and NFT network dynamics, reflecting contemporary digital market challenges. Management Science Marketing Science Journal of Marketing Research Journal of Consumer Research Harvard Business Review Professor Li's publications reveal evolving expertise from foundational pricing elasticity studies toward cutting-edge AI applications in consumer contexts. His work increasingly integrates generative models and graph neural networks to decode complex consumer collection behaviors and digital ecosystem dynamics. Scientific recognition includes being a Finalist for the 2021 Paul E. Green Best Paper Award. Industry impact is demonstrated through executive education programs and strategic consultancies with Tencent, Haier, and Tmall. As Associate Dean for MBA Programs, he oversees curriculum development while maintaining active corporate governance roles on boards of publicly traded companies across China and Hong Kong, directly applying his research insights to strategic decision-making in digital transformation initiatives.

Mengxiao Zhangمشاهده پروفایل

استادیار

• Online learning and bandits
• Reinforcement learning
• Game theory
• +۳ مورد دیگر

Mengxiao Zhang is an Assistant Professor in the Department of Business Analytics at the Tippie College of Business, University of Iowa, holding this position since August 2024. His research develops theoretically grounded machine learning algorithms for practical business applications, with expertise spanning online learning, bandit problems, and game-theoretic optimization. His academic foundation includes: Ph.D. in Computer Science from the University of Southern California (2018-2024), advised by Prof. Haipeng Luo Bachelor's degree from Peking University (2014-2018), advised by Prof. Liwei Wang Zhang's research bridges theoretical machine learning with operational business challenges, focusing on adaptive algorithms that maintain performance guarantees in non-stationary environments. His work addresses core problems in regret minimization, efficient exploration, and equilibrium computation, with increasing emphasis on supply chain optimization, auction design, and fair multi-agent systems. He designs methods that function effectively under constraints like delayed feedback, budget limitations, and unknown demand distributions. Analysis of his 15 most recent publications (2022-2025) reveals a consistent trajectory toward business-relevant applications while maintaining theoretical rigor. Key trends include contextual bandit extensions for advertising auctions, supply chain optimization under uncertainty, and fairness-aware multi-agent learning. His contributions appear in top-tier venues including COLT, ICML, and NeurIPS, with notable recognition including a NeurIPS 2020 Oral presentation. No scientific awards are documented in the provided materials. Zhang teaches Database Management (BAIS-3200) at the University of Iowa and previously served as teaching assistant for multiple graduate algorithms and machine learning courses at USC. No information regarding research grants or student advising is available in the source materials. No dedicated laboratory or research team structure is specified in the provided information.