Find Academic Supervisors

Karl Henrik JohanssonView profile

Professor

• Networked and distributed control
• Cyber-physical systems
• Cyber-secure control systems
• +4 more

Karl Henrik Johansson is a Professor at the School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology in Stockholm, Sweden, where he also serves as the Founding Director of Digital Futures. He is a Fellow of both IEEE and the Royal Swedish Academy of Engineering Sciences, and has held leadership positions including Immediate Past President of the European Control Association and IEEE Control Systems Society Vice President Diversity, Outreach & Development. Dr. Johansson earned his MSc in Electrical Engineering and PhD in Automatic Control from Lund University. His academic journey includes visiting positions at prestigious institutions such as UC Berkeley, Caltech, and NTU. His research focuses on networked control systems and cyber-physical systems with applications in transportation, energy, and automation networks. His work investigates fundamental challenges in connecting physical world systems through communication networks, exploring how wireless communication and sensor technology can enhance system robustness, reliability, energy efficiency, and safety. Current research directions include security of cyber-physical systems, distributed optimization, multi-agent systems, and applications to intelligent transportation and energy networks. Analysis of his recent publications reveals a strong focus on distributed optimization algorithms, secure networked control, multi-agent systems, and applications to transportation and energy networks. His work increasingly integrates machine learning techniques with traditional control theory, addressing challenges in privacy-preserving distributed computation, resilient state estimation, and resource allocation in complex networked systems. IEEE Control Systems Society Hendrik W. Bode Lecture Prize (2024) Swedish Research Council Distinguished Professor (2018-2027) Wallenberg Scholar (2009-2026) IFAC Young Author Prize IEEE CSS Distinguished Lecturer (2017-2019) IFAC Outstanding Service Award IEEE Fellow Dr. Johansson has supervised over 100 postdocs and PhD students, with many now holding prominent positions at institutions worldwide. His research has been supported by significant grants including the Swedish Research Council Distinguished Professor Grant (2018-2027), multiple Wallenberg Foundation grants, and numerous EU and national research projects. He has directed major research centers including ACCESS Linnaeus Centre (2009-2016) and Strategic Research Area ICT TNG (2013-2020). His research group operates within the Digital Futures initiative and maintains strong connections with industry partners through projects like the Integrated Transport Research Lab (supported by Scania and Ericsson) and Smart Mobility Lab. The group actively collaborates with international institutions and participates in major EU-funded projects addressing challenges in cyber-physical systems, transportation, and energy networks.

Benjamin GrimmerView profile

Assistant Professor

• Continuous Optimization
• Algorithms for Machine Learning
• Adversarial Optimization
• +3 more

Benjamin Grimmer is an Assistant Professor in the Department of Applied Mathematics and Statistics at Johns Hopkins University. He is affiliated with the Mathematical Institute for Data Science (MINDS) and the Data Science & AI Institute. His research focuses on designing and analyzing algorithms for continuous optimization, particularly in nonconvex, nonsmooth, and adversarial settings. Grimmer’s work bridges classical optimization theory and modern machine learning challenges, leveraging computer-assisted proof techniques to advance algorithmic foundations. He earned his PhD in Operations Research from Cornell University, advised by Jim Renegar and Damek Davis. His doctoral work was supported by a National Science Foundation fellowship. Grimmer has held research positions at Google and the Simons Institute, exploring adversarial optimization and continuous-discrete optimization interfaces. His current work is supported by the Air Force Office of Scientific Research and a 2024 Alfred P. Sloan Fellowship. Research interests include algorithm design for stochastic/nonconvex/nonsmooth optimization, computer-aided proof methods, and meta-optimization tools like stepsize schedules. His recent studies, including work on gradient descent acceleration via long steps, were highlighted in Quanta Magazine (2023). Education: PhD in Operations Research, Cornell University (advisor: Jim Renegar and Damek Davis) Awards: Alfred P. Sloan Fellowship in Mathematics (2024) National Science Foundation Graduate Fellowship (PhD support) Dr. Grimmer advises a research group including PhD candidates Ning Liu, Thabo Samakhoana, Alan Luner, Yue Wu, and others. His lab explores optimization algorithms through both theoretical and applied lenses, collaborating closely with industry and academic partners.

George MagoulasView profile

Professor

• Machine Learning
• Artificial Intelligence
• Neural Networks
• +7 more

Prof. George Magoulas is a Professor of Computer Science at the University of London's School of Computing and Mathematical Sciences and Director of the Birkbeck Knowledge Lab. He specializes in machine intelligence, machine learning algorithms, and AI system architectures, with applications in healthcare (e.g., neurodegenerative disease diagnosis) and educational technologies. His research has received awards from IEEE, ACM, and others. He holds a PhD in Nonlinear Optimization for Neural Networks and a PGCE in Higher Education. Education: BEng/MEng (Integrated Master's in Systems & Control Engineering), University of Patras, Greece PhD in Nonlinear Optimization for Neural Networks Learning, University of Patras, Greece PGCE in Teaching and Learning (Higher Education) Research & Leadership: He leads the Birkbeck Knowledge Lab, focusing on AI's impact on learning and communication. His work includes designing learning algorithms for psychophysiological data modeling and developing the cloudUPDRS app for Parkinson's disease assessment. He has supervised over 12 PhD students and contributed to 200+ publications. Awards & Recognition: Stanford’s “World’s top 2% of Scientists” (2024) Best Paper Awards at IEEE, ACM, and EUNITE Keynote speaker at major AI and e-learning conferences Honorary membership in the Hellenic Artificial Intelligence Society Administrative Roles: Director of Teaching & Learning Quality (2016–2023) Chair of Postgraduate Programmes Exam Board (2010–2022) Editor-in-Chief, International Journal on Artificial Intelligence Tools Teaching: He teaches courses on Artificial Intelligence, Neural Networks, and Project Management at both undergraduate and postgraduate levels. Labs & Collaborations: He directs the Birkbeck Knowledge Lab and is a member of the Data Science and AI Research Group. His projects include analyzing violent cycles using AI and collaborating on EU-funded initiatives.

Matthew K. TamView profile

Associate Professor

• continuous optimisation and its applications
• monotone operator theory
• variational and convex analysis
• +3 more

Matthew K. Tam is an Associate Professor at the School of Mathematics and Statistics, The University of Melbourne, specializing in Operations Research. He is also an investigator at the Melbourne Centre for Data Science and an associate investigator in the ARC Training Centre OPTIMA. PhD in Mathematics (2016) from University of Newcastle under Jonathan Borwein Postdoctoral research at University of Göttingen with RTG-2088 and Alexander von Humboldt Foundation Junior Professor at University of Göttingen (2017-2020) His research focuses on continuous optimization, monotone operator theory, and variational analysis, with applications in wavelet construction and inverse problems. Key trends include distributed algorithms, resolvent splitting, and convergence analysis for feasibility problems. Discovery Early Career Researcher Award (DECRA) Alexander von Humboldt Fellowship He collaborates with institutions like ANZIAM, Springer, and IEEE, with publications spanning mathematical optimization, harmonic analysis, and computational mathematics. His work emphasizes algorithmic design for complex data systems and real-world applications in imaging and industrial modeling.

Guanghui LanView profile

Professor

• Stochastic Optimization
• Nonlinear Programming
• Machine Learning
• +4 more

Guanghui (George) Lan is the A. Russell Chandler III Chair and Professor in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Institute of Technology . He concurrently serves as Associate Director of Machine Learning and Data Science at Georgia Tech’s Center for Machine Learning . Education: Ph.D. in Industrial and Systems Engineering, Georgia Institute of Technology (2009) Research spans three tightly connected pillars: Theory & Algorithms: stochastic optimization, nonlinear programming, first-order and primal-dual methods. Machine Learning & Data Science: reinforcement learning, policy optimization, minimax formulations, robust learning under uncertainty. Applications: healthcare decision-making, sustainable chemical recycling (PET glycolysis), and resilient biorefining. His 2024–2025 articles reveal a clear trend toward model-free and sampling-efficient algorithms for large-scale or constrained problems, with a parallel emphasis on real-world sustainability applications such as waste-plastic recycling and biorefinery control. Scientific Honors: INFORMS Frederick W. Lanchester Prize (2023) INFORMS Computing Society Prize (2022) NSF CAREER Award (2013) Multiple best-paper and finalist distinctions from INFORMS and the Mathematical Optimization Society Grants & Editorial Service: Funding from NSF, ONR, ARO, USDA, AFOSR, AHA Associate Editor: Computational Optimization and Applications (2014–), Mathematical Programming (2016–), SIAM Journal on Optimization (2016–), Operations Research (2023–) Dr. Lan directs algorithmic development within Georgia Tech’s Center for Machine Learning and advises a vibrant group of Ph.D. students and post-docs working at the intersection of optimization and machine learning.

Damek DavisView profile

Visiting Associate Professor

• Optimization
• Machine Learning
• Signal Processing
• +4 more

Damek Davis is a Visiting Associate Professor at the Wharton Department of Statistics and Data Science at the University of Pennsylvania and an Associate Professor of Operations Research at Cornell University (currently on leave). He held NSF Postdoctoral Fellowships and completed his PhD in Mathematics at UCLA under Wotao Yin and Stefano Soatto. His research bridges optimization , machine learning , statistics , and signal processing , with a focus on convergence guarantees for stochastic and nonsmooth optimization methods. He has developed accelerated gradient descent algorithms, characterized SGD behavior in nonconvex settings, and formalized avoidance of strict saddle points in proximal methods. Key publications include exponential accelerations of gradient-based techniques and first guarantees for SGD on weakly convex functions. His work has been recognized by the Sloan Research Fellowship INFORMS Optimization Society Young Researchers Prize NSF CAREER Award SIAM Activity Group on Optimization Best Paper Prize Davis actively advises Penn graduate students and serves as an associate editor at Mathematical Programming and Foundations of Computational Mathematics . He emphasizes clear technical writing and public communication, maintaining a blog and lecture notes on optimization theory.

• Large-Scale Optimization
• Equilibrium Programming
• Signal Processing
• +4 more

Gesualdo Scutari is an Associate Professor at Purdue University's College of Engineering, Department of Industrial Engineering. He previously served as an Assistant Professor at the State University of New York at Buffalo and held research appointments at UC Berkeley, HKUST, University of Rome, and UIUC. PhD in Electrical Engineering (with honors), University of Rome 'La Sapienza', 2005 BSc in Electrical Engineering (with honors), University of Rome 'La Sapienza', 2001 His research focuses on theoretical and algorithmic aspects of large-scale optimization , including equilibrium programming, decentralized optimization, and distributed decision systems. Applications span signal processing, medical imaging, machine learning, communications, and networking. Key contributions include developing parameter-free decentralized algorithms, adaptive stepsizing methods, and accelerated frameworks for sparse regression and nonconvex optimization. Recent publications demonstrate expertise in decentralized convex/nonconvex optimization , gradient tracking , stochastic methods , and quantized algorithms . His work often addresses statistical guarantees, convergence rates, and high-dimensional optimization problems. 2020 IEEE Signal Processing Society Best Paper Award 2013 NSF CAREER Award 2013 UB Young Investigator Award Dr. Scutari serves as Associate Editor for IEEE Transactions on Signal Processing and IEEE Transactions on Signal and Information Processing over Networks. He is active in the IEEE Signal Processing Society Technical Committee on Signal Processing for Communications.

Yongqiang WangView profile

Professor

• Distributed Control
• Optimization
• Machine Learning
• +3 more

Yongqiang Wang serves as Professor in Clemson University's Department of Electrical and Computer Engineering, leading the Network Systems and Control research group with expertise spanning distributed optimization, cyber-physical security, and resilient synchronization systems. Education: Ph.D. in Control Science & Engineering, Tsinghua University (2009) Dual B.S. degrees: Electrical Engineering & Automation and Computer Science & Technology, Xi'an Jiaotong University (2004) His research pioneers privacy-preserving distributed algorithms for cyber-physical systems, with breakthroughs in differentially-private optimization that maintain convergence accuracy while protecting sensitive data. Current work addresses saddle-point avoidance in nonconvex learning (featured in PNAS) and bio-inspired clock synchronization resilient to GPS spoofing attacks. The group develops foundational theory for power grids, robot networks, and automotive systems. Publication trends reveal intense focus on differential privacy in distributed optimization (14+ papers in 2023-2024), with applications spanning multi-agent reinforcement learning for vehicle platooning and secure consensus protocols. Key disciplines include control theory, machine learning, and network security. Awards: 2008 IFAC Young Author Prize (Japan Foundation) Dr. Wang actively mentors 7 current graduate students including PhD candidates researching privacy-preserving optimization (Zhang), attack-resilient synchronization (Wang), and pulse-coupled oscillators (Anglea). Alumni include Francesco Ferrante (now Assistant Professor at University of Grenoble) and Hafiz Ahmad (Lecturer at Coventry University). His NSF-funded research includes secure time synchronization and cooperative vehicle control projects. The Network Systems and Control group operates from Clemson's Fluor Daniel Building, collaborating with industry partners on GPS spoofing detection and multi-robot formation control using state-decomposition techniques. Outreach includes mentoring high school STEM projects and judging robotics competitions.

Damek DavisView profile

Assistant Professor

• Optimization
• Machine Learning
• Signal Processing
• +4 more

Damek Davis is an Assistant Professor in the Department of Mathematics at Cornell University, affiliated with both the College of Engineering and the College of Arts and Sciences. He holds a Ph.D. in Mathematics from the University of California, Los Angeles (2015). His research focuses on developing and analyzing optimization algorithms for large-scale, nonconvex, and nonsmooth problems arising in machine learning and signal processing. He emphasizes theoretical guarantees on algorithm performance and practical implementations that leverage modern computing architectures. His work spans stochastic optimization, subgradient methods, and convergence analysis, with applications to computational microscopy, phase retrieval, and decentralized systems. Recent contributions include advancements in adaptive stepsize methods, sharpness-aware optimization, and global optimality conditions for mixture models. Davis collaborates on theoretical foundations and algorithmic innovations in high-dimensional statistics, nonlinear optimization, and parallel computing. His scholarly output includes over 50 peer-reviewed articles, with recent highlights in top venues such as SIAM Journal on Optimization, Mathematical Programming, and IEEE Transactions on Signal Processing. His research is supported by grants from NSF and AFOSR, focusing on topics like robust statistical estimation and algorithmic scalability.

Yangyang XuView profile

Associate Professor

• Stochastic Optimization
• Nonlinear Programming
• Computational Optimization
• +4 more

Yangyang Xu is an Associate Professor in the Department of Mathematical Sciences at Rensselaer Polytechnic Institute (RPI), where he conducts research at the intersection of optimization theory and computational methods. His work bridges theoretical foundations with practical applications in machine learning and data science. Dr. Xu's research focuses on several interconnected areas: Continuous optimization : specializing in stochastic programming, distributed optimization, and tensor optimization Optimization methods : developing stochastic approximation techniques, first-order methods, block update methods, and operator splitting approaches Computational frameworks : advancing parallel and distributed computing implementations for large-scale optimization problems Applications : applying optimization techniques to machine learning, signal processing, compressed sensing, and data mining challenges His recent publications (2023-2025) demonstrate a clear progression toward increasingly sophisticated optimization frameworks, particularly in decentralized and stochastic settings. Xu has made significant contributions to nonconvex optimization, minimax problems, and constrained optimization, with his work showing strong theoretical foundations coupled with practical implementations. Dr. Xu serves on the editorial board of Mathematics of Operations Research (since January 2023), reflecting his standing in the optimization community. He actively mentors six PhD students and has successfully guided multiple students to completion, with graduates moving to positions at organizations including Evonik, SAS, and UT Austin. His teaching includes graduate courses such as Stochastic Optimization and Reinforcement Learning and Introduction to Optimization. Dr. Xu leads a research group focused on advancing optimization theory while developing practical algorithms for real-world applications, particularly in distributed computing environments where communication efficiency is critical.

• Numerical Analysis
• Ordinary Differential Equations (ODEs)
• Differential-Algebraic Equations (DAEs)
• +5 more

Dr. Helmut Podhaisky is a researcher at the Institute of Mathematics , Martin Luther University Halle-Wittenberg , within the Faculty of Natural Sciences II. His work focuses on numerical methods for differential equations, particularly stiff ODEs, DAEs, and Volterra equations. Email: podhaisky@mathematik.uni-halle.de Research Interests: Numerical methods for stiff and oscillatory differential equations Runge-Kutta and peer methods Parallel computing algorithms Mathematical modeling of calcium waves in biological systems Recent Publications highlight his work on barycentric rational methods, adaptive integrators, and bifurcation analysis in oscillating systems. His research spans both theoretical developments and practical applications in computational mathematics.

Niao HeView profile

Associate Professor

• Machine Learning
• Optimization
• Reinforcement Learning
• +4 more

Prof. Niao He is an Associate Professor in the Department of Computer Science at ETH Zürich. His research focuses on optimization theory, reinforcement learning, stochastic systems, and their applications in machine learning and multi-agent systems. He holds an academic position at one of the world's leading technical universities, contributing to both theoretical advancements and practical algorithmic solutions. His research interests span optimization theory (e.g., convex/non-convex optimization, stochastic optimization), reinforcement learning (policy gradient methods, multi-agent systems), and statistical learning (risk-averse methods, entropy regularization). He has also explored applications in data science, network revenue management, and deep reinforcement learning for complex systems. Recent work emphasizes algorithmic reproducibility, robustness under model uncertainty, and efficient methods for large-scale problems. Notable contributions include novel approaches to minimax optimization, mean-field games, and adaptive learning frameworks. His articles consistently address theoretical guarantees while maintaining practical relevance for real-world computational challenges.

Courtney PaquetteView profile

Assistant Professor

• Large-scale Optimization
• Nonconvex Optimization
• Nonsmooth Analysis
• +4 more

Courtney Paquette is an Assistant Professor in the Department of Mathematics and Statistics at McGill University, a CIFAR AI Chair at MILA, and a part-time Research Scientist at Google DeepMind. She specializes in large-scale optimization, stochastic algorithms, and high-dimensional statistics, with cross-disciplinary applications in machine learning. Her research integrates tools from probability, complexity theory, and nonsmooth analysis to develop theoretical guarantees for modern data science challenges. She holds a Ph.D. in Mathematics from the University of Washington (2017), followed by postdoctoral positions at Lehigh University and the University of Waterloo under an NSF fellowship. Her educational background strengthens her focus on foundational optimization and algorithmic theory. Research Interests: Dr. Paquette's work centers on: Nonconvex and nonsmooth optimization for large-scale problems Stochastic algorithms and their high-dimensional dynamics Interactions between random matrix theory and machine learning Average-case complexity of learning algorithms Her recent publications explore exact risk trajectories of SGD, neural scaling laws, and privacy-preserving optimization. Awards & Honors: Sloan Fellowship in Computer Science (2024) REACH Magazine Rising Star in AI (2022) NSF Postdoctoral Fellowship (2018–2019) CIFAR AI Chair at MILA Advising & Grants: She mentors multiple Ph.D. and Master's students, with research supported by NSERC Discovery Grants, FRQNT startup funding, and CIFAR. She co-leads the OPT-ML Workshop at NeurIPS and the HiLD Workshop at ICML. Labs & Teams: Dr. Paquette is an active member of the Montreal Machine Learning Optimization Group (MTL MLOpt) at MILA and collaborates with Google DeepMind. She founded McGill's RMT+ML+OPT seminar series to foster student engagement in optimization research.

Yan HuangView profile

Researcher

• Distributed Optimization
• Federated Optimization
• Large-Scale Machine Learning
• +5 more

Yan Huang (黄炎) is a postdoctoral researcher at KTH Royal Institute of Technology, affiliated with the Division of Decision and Control Systems. He earned his Ph.D. in Control Science and Control Engineering from Zhejiang University (2020-2024) under Prof. Jinming Xu and Prof. Jiming Chen, with prior degrees from Southeast University and Anhui University. His work focuses on distributed optimization and machine learning. Ph.D. in Control Science and Control Engineering, Zhejiang University, 2020-2024 M.S. in Control Science and Control Engineering, Southeast University, 2017-2020 B.S. in Automation, Anhui University, 2013-2017 Yan Huang specializes in distributed and federated optimization theory , applying these techniques to large-scale machine learning and networked control systems . His research addresses data heterogeneity, robustness to failures, and computational efficiency in decentralized networks. He has developed flexible frameworks for gradient tracking and personalized optimization. His recent publications emphasize stochastic gradient tracking , variance reduction , and differential privacy in distributed settings. Key topics include adaptive stepsizes , Byzantine-robust algorithms , and computation-communication trade-offs , reflecting his focus on scalable and secure optimization methods. Outstanding Graduate, Zhejiang University, 2024 Outstanding Doctoral Student, Zhejiang University, 2022 and 2023 2nd prize in China Post-graduate Mathematical Contest in Modeling, 2017 Outstanding Graduate, Anhui University, 2017 Huang has taught courses on Principles of Automatic Control , Modern Control Theory , and Distributed Control and Optimization . He has also presented at ICML 2022 and Zhejiang University's academic forum, highlighting his work on decentralized SGD and data heterogeneity.

Jingfeng WuView profile

Research Fellow

• Deep Learning Theory
• Optimization
• Statistical Learning
• +2 more

Jingfeng Wu is a postdoctoral fellow at the Simons Institute for the Theory of Computing at UC Berkeley, hosted by Peter Bartlett and Bin Yu. He contributes to the NSF/Simons Collaboration on the Theoretical Foundations of Deep Learning, focusing on advancing core machine learning theory. His academic journey includes a Ph.D. in Computer Science from Johns Hopkins University (2023), an M.S. in Applied Mathematics from Peking University (2019), and a B.S. in Mathematics from Peking University (2016). This strong mathematical foundation underpins his theoretical research approach. Wu's research centers on deep learning theory, optimization algorithms, and statistical learning. He investigates implicit regularization in gradient descent, scaling laws in linear models, and the dynamics of large-stepsize optimization. His work reveals how non-monotonic loss landscapes and adaptive stepsizes accelerate convergence in logistic regression and deep networks, providing fundamental insights into generalization in overparameterized regimes. Analysis of his 15 most recent publications shows a cohesive research program examining stochastic optimization in machine learning. Key themes include the interplay between stepsize selection and convergence rates, the role of data structure in scaling laws, and implicit bias mechanisms in neural networks. His work consistently bridges theoretical guarantees with practical algorithmic implications. Scientific recognition includes: Rising Star in Data Science (2023) by University of Chicago and UC San Diego MINDS Summer Data Science Fellowship (2021) Wu actively serves the research community as an organizer of the 2025 Deep Learning Theory Workshop at Simons Institute and as a reviewer for ICML (2020-2025), NeurIPS (2020-2025), and other top venues. His current work is supported by the NSF/Simons Collaboration grant. He collaborates extensively with leading researchers including Peter Bartlett, Bin Yu, and Vladimir Braverman within the Simons Institute ecosystem, contributing to its vibrant theoretical machine learning community through seminars and collaborative projects.