جستجوی استاد راهنمای دانشگاهی

Athina Tzovaraمشاهده پروفایل

استاد

• Cognitive Neuroscience
• Machine Learning
• Computational Neuroscience
• +۷ مورد دیگر

Prof. Athina Tzovara is a Professor at the University of Bern, leading the Cognitive Computational Neuroscience (CCN) research group within the Institute of Computer Science (Faculty of Science) with a dual affiliation in the Department of Neurology (Faculty of Medicine). Her research integrates computational modeling, machine learning, and neural recordings to study cognitive processes and neurological conditions. Key areas include sleep dynamics, coma prognosis, AI-driven healthcare solutions, and neural mechanisms underlying consciousness. Education: BEng in Electrical & Computer Engineering (National Technical University of Athens, 2009), PhD in Neuroscience (University Hospital Centre Lausanne, 2012). Postdoctoral roles at University of Zurich and University College London preceded her current position. Research focuses on: (1) Sleep-wake disorders using EEG and causal inference approaches, (2) Predictive neural coding models for auditory processing in coma patients, (3) Ethical AI frameworks for automated medical diagnostics, and (4) Data-driven phenotyping of neurological conditions. Recent work emphasizes translating computational neuroscience insights into clinical tools - such as EEG-based coma outcome prediction and bias-aware sleep scoring algorithms. Her lab collaborates internationally on initiatives like SPHYNCS (narcolepsy cohort study) and Brain Mappers for open neuroscience communication. Advocates for inclusive scientific practices through gender bias mitigation strategies and multilingual dissemination efforts. Active in Open Science initiatives like Open Humans platform development.

Francesca Dalia Faraciمشاهده پروفایل

مدرس ارشد

• Biomedical Signal Processing
• Medical Data Analysis
• Wearable Technology
• +۵ مورد دیگر

Francesca Dalia Faraci is a Senior Lecturer and Researcher at the Department of Innovative Technologies (DTI) of SUPSI. She holds a PhD in Electronics from the University of York (UK) and a Laurea in Physics from the University of Genoa (Italy). Her research focuses on biomedical signal processing, statistical data analysis, and wearable technology applications in healthcare. She leads projects such as Cardio MIPA (arrhythmia monitoring) and AutoPlay_DD (child development analysis via smart toys). Key contributions include developing algorithms for sleep staging, arrhythmia detection, and synthetic ECG generation. Awards include the GOSPEL and DoE School Certificates. She coordinates research projects and teaches courses in Physics and Applied Statistics. Education: PhD in Electronics (University of York, 2006), Laurea in Physics (University of Genoa, 2002) Roles: Senior Lecturer, Researcher, Project Coordinator Key Projects: Tackling teleWorking Impacts, my Doctor's Lifestyle (lifestyle medicine), Telemonitoring Breast Cancer Her research bridges AI and clinical practice, emphasizing ethical frameworks and complementarity between clinicians and AI systems. Recent work includes causal inference for sleep dynamics and bias quantification in healthcare algorithms.

Renata Borovica-Gajicمشاهده پروفایل

دانشیار

• Database Systems
• Machine Learning
• Artificial Intelligence
• +۱۲ مورد دیگر

Renata Borovica-Gajic is an Associate Professor in Data Analytics and an ARC DECRA Fellow at the School of Computing and Information Systems (CIS), University of Melbourne. She also serves as Associate Dean (Diversity and Inclusion) for the Faculty of Engineering and IT, demonstrating leadership in both research and academic community development. Her research lies at the intersection of database systems, machine learning, and artificial intelligence, with a vision of creating adaptive, self-driving database engines that optimize query execution in real-time. Her work spans learned indexes, query optimization, data quality, and data-driven traffic optimization, aiming to reduce costs and improve performance in data analytics. The recent publications reflect a strong trend toward integrating machine learning into core database operations—particularly through learned indexes, bandit-based tuning, and reinforcement learning for traffic systems. These works emphasize automation, provable guarantees, and real-time adaptation, showcasing a cohesive research agenda focused on intelligent, self-optimizing data systems. Her scientific excellence is recognized by numerous awards, including: L'Oréal-UNESCO for Women in Science Fellowship (2023) Victorian Young Tall Poppy (2024) Test of Time Award at SIGMOD 2022 Multiple Research and Teaching Excellence Awards from the University of Melbourne Google Research Inclusion Award (2021) She actively mentors PhD students and leads significant research projects funded by the Australian Research Council, Google, and Telstra. Her service includes roles as Associate Editor for SIGMOD Record, conference organization (e.g., aiDM, ADC, VLDB), and leadership in diversity and inclusion initiatives. She has also contributed to influential publications such as a chapter in the 7th edition of Database System Concepts . Her research lab focuses on AI-powered databases, traffic optimization via reinforcement learning, and self-healing data systems, positioning her at the forefront of next-generation data management.

Debabrota Basuمشاهده پروفایل

استادیار

• Machine Learning
• Reinforcement Learning
• Bandit Algorithms
• +۶ مورد دیگر

Debabrota Basu is a tenured faculty member (Inria Starting Faculty Position - ISFP) at the Scool team (previously called SequeL) of Inria Centre at University of Lille in France. He teaches postgraduate-level courses on privacy, responsible machine learning, and research methods in AI at École normale supérieure-PSL University, Université de Lille, and Centrale Lille. He is also a member of the ELLIS Society (European Laboratory for Learning and Intelligent Systems) and the Paris unit of ELLIS. Dr. Basu earned his PhD in Computer Science from the Department of Computer Science, School of Computing, National University of Singapore, advised by Stéphane Bressan and Pierre Senellart. Prior to that, he obtained a B.E. degree with Honours in Electronics and Telecommunication Engineering from Jadavpur University. Before joining Inria, he was a postdoctoral researcher at Chalmers University of Technology's Data Science and AI Division. Dr. Basu's research focuses on constructing algorithms for developing efficient, robust, private, and ethical learning machines that solve real-world problems. His methodological approach blends statistics, machine learning, and optimization. His application interests span sustainable agro-ecology, medical and pharmaceutical applications, energy-efficient autonomous systems, and algorithmic audits. Recent collaborations include the Inria-Indian Statistical Institute associate team SeRAI for developing Sequential Testing and Learning Algorithms for Verifiably Robust and Responsible AI, and the Inria-INRAE collaboration on Resilient Agricultural Decision Making under Environmental Risks. His publication record demonstrates expertise in bandit algorithms, reinforcement learning, and privacy-preserving machine learning. Recent work shows a strong theoretical foundation with practical applications, particularly in pure exploration bandits, differential privacy mechanisms, constrained optimization, and fairness verification. His research bridges the gap between theoretical guarantees and real-world deployment challenges across multiple domains. Dr. Basu has received notable recognition for his contributions: Best Student Paper Award at ACM EAAMO 2022 for 'On Meritocracy in Optimal Set Selection' Young researcher (JCJC) grant from the French National Research Agency (ANR) in 2022 in 'Artificial Intelligence and Data Science' He leads the project 'RL under Real-life Constraints: Regrets and Algorithms' and supervises PhD students and postdoctoral researchers. His research is supported by multiple projects including REPUBLIC ('Vers l'IA responsable avec l'apprentissage par renforcement sous contraintes') and 'Foundations of robustness and reliability in artificial intelligence.' Dr. Basu actively collaborates with institutions worldwide, including establishing the RELIANT associate team with Kyoto University for investigating structured multi-armed bandit problems.

Suryanarayana Sankagiriمشاهده پروفایل

پژوهشگر

• Discrete Choice Models
• Recommendation Systems
• Blockchain Security
• +۴ مورد دیگر

Suryanarayana Sankagiri is a postdoctoral researcher at the École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland, affiliated with the Information and Network Dynamics (INDY1) group under Professor Matthias Grossglauser. Previously, he earned his Ph.D. in Electrical & Computer Engineering (2018-2022) from the University of Illinois at Urbana-Champaign , where he was supervised by Bruce Hajek and participated in the Coordinated Science Lab . He also holds an M.S. in Electrical & Computer Engineering from the University of Illinois (2016-2018) and a B.Tech. in Electrical Engineering from the Indian Institute of Technology Bombay (2012-2016). Education : Ph.D., Electrical & Computer Engineering, University of Illinois (2018-2022) M.S., Electrical & Computer Engineering, University of Illinois (2016-2018) B.Tech., Electrical Engineering, IIT Bombay (2012-2016) Suryanarayana's research focuses on discrete choice models and their application to recommendation systems , with a particular emphasis on learning from choice data and developing novel models for human decision-making. His broader interests include blockchain security under adverse network conditions, network dynamics , probabilistic modeling , and algorithm design . Recent work explores nonconvex matrix factorization and contextual dueling bandits for recommendation systems. His publications span theoretical and applied domains, including high-impact venues like ICML , Stochastic Systems , and IEEE Transactions on Networking . Themes include blockchain efficiency , hidden community detection in preferential attachment graphs, and temporal analysis of Indian classical music. Current projects involve refining recommendation systems through sparse comparison data and designing protocols for resilient blockchain networks. Scientific Awards : zkCapital Paper of the Week (2021) Rambus Fellowship (2021) Mavis Future Faculty Fellowship (2019) List of Teachers Ranked as Excellent (2019) Nomination for IIT Bombay Undergraduate Colloquium (2016) Best Poster Award, IIT Bombay Undergraduate Research Symposium (2013) Suryanarayana has advised no students listed in the provided materials. His work has been supported by fellowships such as the Mavis Future Faculty Fellowship and Rambus Fellowship . He contributes to the INDY1 group at EPFL, which investigates information and network dynamics through interdisciplinary approaches combining probability , network theory , and algorithmic design .

• Algorithmic Sequential Decision-Making
• Robust AI
• Safe AI
• +۱۱ مورد دیگر

Ilija Bogunovic is an Assistant Professor (UK Lecturer) in the Department of Electronic and Electrical Engineering at University College London (UCL), Faculty of Engineering Sciences. His research focuses on algorithmic sequential decision-making for robust, reliable, and safe artificial intelligence, with applications in large language model alignment, reinforcement learning, and human feedback integration. His research interests lie at the intersection of machine learning, optimization, and decision theory. He investigates robustness in Bayesian optimization, bandits, and reinforcement learning under adversarial attacks, model misspecification, and distributional shifts. His work spans both theoretical foundations and real-world applications in energy systems, mobility, and AI safety. A central theme is developing algorithms that are provably robust and efficient in uncertain and potentially corrupted environments. The recent publications highlight a strong trend in robust decision-making, particularly in reinforcement learning and preference optimization. Key themes include adversarial robustness in large models, distributional robustness in RL, safe multi-agent systems, and robust Bayesian optimization. The work frequently involves theoretical analysis of regret and sample complexity, combined with practical algorithm design for high-impact applications. Scientific Awards: Google Research Scholar Program Award (Machine Learning & Data Mining), 2023 EPSRC New Investigator Award, 2023 Ilija Bogunovic actively supervises PhD and MSc students, with several of his advisees leading papers accepted to top venues like NeurIPS and ICLR. He has secured competitive research grants, including the EPSRC New Investigator Award, to support his work on robust decision-making. He is building a research team focused on robust and safe AI. He leads a research team and has initiated an online reading group on modern adaptive experimental design and active learning, fostering a collaborative research environment.

Maryam Kamgarpourمشاهده پروفایل

استادیار

• Control Theory
• Game Theory
• Mechanism Design
• +۶ مورد دیگر

Maryam Kamgarpour is a Tenure Track Assistant Professor at École Polytechnique Fédérale de Lausanne (EPFL), School of Engineering. She previously held faculty positions at the University of British Columbia and ETH Zürich. Her work bridges stochastic control , multiagent learning , and game theory , focusing on safety-critical systems. Education: PhD in Engineering from UC Berkeley, BSc in Applied Science from University of Waterloo. Research Interests: Control under uncertainty, game theory, mechanism design, mixed-integer optimization, and applications to transportation, robotics, power grids, and healthcare. Her recent publications emphasize safe reinforcement learning , multirobot coordination , and stochastic trajectory planning , with applications to aircraft navigation and energy systems. She has received the European Union ERC Starting Grant, NASA High Potential Individual Award, and IEEE Transactions on Control of Network Systems Outstanding Paper Award. Scientific Awards: ERC Starting Grant (2016-2021) NASA High Potential Individual Award (2010) NASA Excellence in Publication Award IEEE Outstanding Paper Award (2022) PhD Students: Jordan Philip Christopher Maddux Anna Maria Ni Tingting Ren Kai Salizzoni Giulio Schlaginhaufen Andreas Vaishampayan Saurabh Dilip Vallat Gabriel Rémi Former EPFL student: Guo Baiwei

• Online learning
• Optimization theory
• Bandits
• +۲ مورد دیگر

Tommaso Cesari serves as an Assistant Professor in the EECS department at the University of Ottawa, cross-appointed with the Department of Mathematics and Statistics. He currently teaches Machine Learning (CSI 4145) and Introduction to Computing II (ITI 1121 A), courses he has instructed since 2024 and 2023 respectively. His research centers on theoretical machine learning with applications in market design and operational systems. Key interests include online learning frameworks for bandit problems, pricing mechanisms, bilateral trade optimization, and spacecraft operations scheduling. This work bridges algorithmic theory with real-world economic systems, emphasizing regret minimization under adversarial conditions and smoothed analysis. Analysis of his 2023-2025 publications reveals a cohesive trajectory in applying online learning to bilateral trade mechanisms (appearing in 7 of 15 recent papers), auction theory, and brokerage models. His work consistently targets top venues including JMLR, NeurIPS, and STOC, with growing emphasis on fairness constraints and multi-platform systems in 2024-2025 outputs. Professor Cesari actively recruits Master's and Ph.D. students for research in his domains; prospective candidates may apply through the university portal. His collaborative publications with prominent researchers like Nicolò Cesa-Bianchi indicate strong engagement in the theoretical machine learning community.

Luca Vianoمشاهده پروفایل

پژوهشگر

• Reinforcement Learning
• Game Theory
• Imitation Learning
• +۳ مورد دیگر

Luca Viano is a Doctoral Assistant and ELLIS PhD Fellow at EPFL's Laboratory for Information and Inference Systems (LIONS), affiliated with the School of Engineering (STI) and the Institute of Electrical Engineering (IEM). His research focuses on reinforcement learning, game theory, and imitation learning, supported by the Swiss Data Science Center and EPFL's EDIC Excellence Fellowship. Education: MSc in Computational Science and Engineering, with a final project supervised by Johanni Brea and Wulfram Gerstner. Previously worked as a Data Scientist at Datapred. Research interests include multi-agent systems, online learning algorithms, and theoretical guarantees for RL methods. Recent work emphasizes imitation learning in linear MDPs, regret minimization in congestion games, and robust alignment of large language models with human feedback. Key achievements include COLT 2025 and ICML 2024 acceptances, a NeurIPS 2023 spotlight presentation, and co-organizing the Virtual RL Theory Seminars and Multi-Agent RL Summer School. Active in the RL community with collaborations at Swiss Data Science Center. Advising: Supervised by Professors Volkan Cevher and Gergely Neu. Grants include support from ELLIS and Swiss Data Science Center. Labs/Teams: Core member of LIONS lab, collaborating internationally on RL theory and applications.

Melih Kandemirمشاهده پروفایل

دانشیار

• Machine Learning
• Bayesian Inference
• Stochastic Process Modeling
• +۵ مورد دیگر

Melih Kandemir is an Associate Professor of Machine Learning at the University of Southern Denmark, Department of Mathematics and Computer Science. He earned his PhD in 2013 from Aalto University under Prof. Samuel Kaski, followed by postdoctoral work at Heidelberg University (with Prof. Fred Hamprecht) and an assistant professorship at Ozyegin University, Turkey. Prior to joining SDU, he led research at Bosch Center for Artificial Intelligence. Education: PhD (Aalto University, 2013), Postdoc (Heidelberg University). Previous Roles: Assistant Professor (Ozyegin University), Research Group Leader (Bosch CAI). His research focuses on Bayesian inference, stochastic process modeling with deep neural networks, and applications to reinforcement learning and continual learning. He leads the SDU Adaptive Intelligence (ADIN) Lab and is an ELLIS Member, reflecting his standing as a top European AI researcher. His work addresses critical challenges in uncertainty quantification, exploration strategies, and theoretically grounded algorithms for decision-making systems. Recent publications highlight expertise in model-based reinforcement learning (e.g., MOMBO for offline RL), PAC-Bayesian bandits, evidential learning for robust classification, and neural stochastic differential equations. His scientific awards include a Best Paper Award (2017) and ELLIS Membership. He also explores interdisciplinary applications of natural sciences to sustainable technology development.

Tobias Heilmannمشاهده پروفایل

مدرس

• Statistical Inference
• Change Point Detection
• Differential Privacy
• +۵ مورد دیگر

Dr. Tobias Heilmann is a Lecturer at the Department of Humanities, Social and Political Sciences at ETH Zurich. His research focuses on statistical inference, change point detection, differential privacy, high-dimensional data analysis, network analysis, and machine learning. He holds a PhD in Statistics from Fudan University, advised by Zhiliang Ying, and has contributed to software packages such as changepoints , GMPro , and APPLE . His work bridges theoretical statistics and practical applications, emphasizing privacy-preserving techniques, dynamic systems analysis, and algorithmic robustness. Key areas include nonparametric methods, contextual bandits, federated learning, and functional data analysis. Recent contributions address challenges in distributed systems, adversarial robustness, and high-dimensional model selection. He has published extensively in top journals like Annals of Statistics , SIAM Journal on Mathematics of Data Science , and IEEE Transactions on Information Theory . Dr. Heilmann's research also involves interdisciplinary collaborations, including social psychology of groups and biomedical applications. His software tools are widely used for change point analysis and community detection in networks. Current projects explore optimal privacy-utility trade-offs and adaptive algorithms for non-stationary environments.

Ramzi Sofiane Dakhmoucheمشاهده پروفایل

پژوهشگر

• Graph Time Series Forecasting
• Graph Reinforcement Learning
• Machine Learning
• +۴ مورد دیگر

Ramzi Sofiane Dakhmouche is a doctoral student in mathematics at École Polytechnique Fédérale de Lausanne (EPFL) within the School of Basic Sciences (SB), Department of Mathematics (MATH), and the Statistical Field Theory Chair (CSFT). He holds the role of Researcher/Assistant-doctorant at CSFT and serves as President of the SIAM Student Chapter at EPFL. His research focuses on Graph Time Series Forecasting, Graph Reinforcement Learning, and applications in biological/engineering systems. He has contributed to works on robust symbolic regression and topological uncertainty in deep learning, including a provisional patent for a multi-task bandits method. His education includes an MSc in Mathematics, Vision, Learning from École Normale Supérieure Paris-Saclé. Research interests span machine learning theory, uncertainty quantification, and operator learning. Notable works include submissions on robust deep operator learning and papers under preparation on network system forecasting and scalable symbolic regression. He actively writes technical Medium articles on topics like proximal gradient optimization and generalization error analysis.

Matteo Castiglioniمشاهده پروفایل

استادیار

• Artificial Intelligence
• Algorithmic Game Theory
• Machine Learning
• +۵ مورد دیگر

Matteo Castiglioni is an assistant professor (RTD-A) at the Department of Electronics, Information and Bioengineering (DEIB) at Politecnico di Milano. He received his PhD in computer science from the same institution under the supervision of Prof. Nicola Gatti. His academic career spans multiple teaching roles across various programs at Politecnico di Milano. Castiglioni's research focuses on the intersection of artificial intelligence, algorithmic game theory, and multi-agent systems. He specializes in combining machine learning techniques with economic paradigms to build strategic agents capable of operating in complex multi-agent environments. His work addresses fundamental challenges in contract theory, mechanism design, and strategic decision-making under uncertainty. His publication record shows a clear trajectory toward increasingly sophisticated models that integrate learning with strategic behavior. Recent papers demonstrate expertise in constrained optimization, regret minimization, and handling both stochastic and adversarial environments. His work bridges theoretical computer science with practical applications in economics and market design. Castiglioni has taught across multiple academic levels including B.Sc., M.Sc., and Ph.D. programs. He has served as both professor and teaching assistant for courses in Game Theory, Online Learning Applications, and Computer Science and Engineering programs.

Bingcong Liمشاهده پروفایل

پژوهشگر

• Machine Learning
• Optimization
• Signal Processing
• +۳ مورد دیگر

Bingcong Li is a postdoctoral researcher at ETH Zurich collaborating with Prof. Niao He and the ODI group. Previously, they completed doctoral studies at the University of Minnesota under Prof. Georgios B. Giannakis, followed by industry experience focused on large language models (LLMs). Education includes a PhD from the University of Minnesota under Prof. Georgios B. Giannakis. Research centers on making computation efficient, accessible, and affordable across heterogeneous resources—from GPU clusters to consumer hardware—through interdisciplinary approaches combining deep learning, optimization, and signal processing. Key research areas address foundational computing architectures, large-scale system sustainability, and personalized AI access. Their work develops theoretically grounded methods for explainable systems, with recent focus on LLM fine-tuning efficiency. Publication trends show consistent contributions to top conferences (NeurIPS, ICML, ICLR) with emphasis on optimization techniques for resource-constrained LLM deployment. Their advising and grant activities aren't explicitly detailed, though they actively participate in academic service through conference talks (EUROPT 2025, ICASSP 2025) and co-organizing events like the Efficient LLMs Fine-tuning Track at AI+X Summit. Lab affiliation centers on ETH Zurich's ODI group under Prof. Niao He, focusing on optimization-driven AI solutions.

Anastasios Tsiamisمشاهده پروفایل

مدرس

• Statistical Learning and Control
• Data-Driven Control
• Online Learning
• +۳ مورد دیگر

Dr. Anastasios Tsiamis is a Lecturer at the Department of Information Technology and Electrical Engineering at ETH Zürich, working in the Automatic Control Laboratory (Professur Control and Computation). His research focuses on the intersection of control theory and machine learning, specifically investigating how system theoretic properties affect the statistical difficulty of learning in system identification, online estimation, and control. Dr. Tsiamis received his Diploma (MEng, five-year degree) in Electrical and Computer Engineering from the National Technical University of Athens (NTUA). He completed his Ph.D. in Electrical and Systems Engineering at the University of Pennsylvania under Professor George Pappas, following graduate research with Professor Petros Maragos and undergraduate work with Professor Kostas J. Kyriakopoulos at NTUA. His primary research areas include Statistical Learning and Control, Data-Driven Control, Online Learning, Risk-Aware Control, and Security and Privacy in Networked Control Systems. Dr. Tsiamis has made significant contributions to understanding the fundamental statistical limits of learning in control systems, particularly focusing on sample complexity. His work on risk-aware optimization develops algorithms that safeguard against catastrophic events while maintaining good average performance, and his security research addresses eavesdropping attacks in remote estimation and motion planning. Analysis of Dr. Tsiamis's recent publications reveals a strong focus on data-driven approaches to control theory with emphasis on distributionally robust methods, risk-aware optimization, and finite sample guarantees. His work bridges theoretical foundations with practical applications across system identification, online learning, and adaptive control, providing rigorous non-asymptotic guarantees for learning-based control algorithms. Dr. Tsiamis has received several notable research recognitions: Best student paper award at IEEE 61th Conference on Decision and Control (2022) Spotlight Presentation at 41st International Conference on Machine Learning (2024) Finalist for best student paper award at American Control Conference (2019) Finalist for young author prize at IFAC World Congress (2017) Oral presentation at 2nd L4DC Conference (2020) Dr. Tsiamis teaches Linear System Theory (227-0225-00L) at ETH Zürich and collaborates extensively with Professor John Lygeros, Professor Manfred Morari, and researchers from the University of Pennsylvania. His publication record demonstrates strong collaborative research across multiple institutions while advancing theoretical foundations of learning-based control. As an active member of the Automatic Control Laboratory at ETH Zürich, Dr. Tsiamis contributes to advancing control systems science through rigorous mathematical analysis and innovative algorithmic development, with applications spanning robotics, energy systems, and networked control.