Find Academic Supervisors

Andrew ChildsView profile

Professor

• Quantum Algorithms
• Quantum Information Processing
• Quantum Simulation
• +2 more

Andrew Childs is a Professor at the University of Maryland, affiliated with the Department of Computer Science and the Institute for Advanced Computer Studies (UMIACS). He serves as Director of the NSF Quantum Leap Challenge Institute for Robust Quantum Simulation (RQS) and is a Fellow at the Joint Center for Quantum Information and Computer Science (QuICS). His research focuses on quantum algorithms for simulating physical systems, algebraic problems, and quantum walk protocols, with applications in quantum computing and computational complexity. University of Maryland Institute for Advanced Computer Studies (UMIACS) Joint Center for Quantum Information and Computer Science (QuICS) NSF Quantum Leap Challenge Institute for Robust Quantum Simulation Childs' research spans quantum simulation, quantum Fourier transform, phase estimation, and Hamiltonian dynamics. He has developed techniques to reduce quantum computational resources for simulating quantum systems and explored limitations of quantum computers through hidden subgroup problems and non-unitary dynamics. His publications cover diverse areas including quantum walk optimization, Hamiltonian simulation methods, and applications to cryptography and condensed matter physics. Recent works address spatial search algorithms, product formulas for commutators, and quantum routing protocols. As an educator, Childs has taught courses on quantum algorithms and information processing at both the University of Maryland and University of Waterloo, with lecture notes and materials spanning multiple years. Contact: amchilds@umd.edu | Office: ATL 3359 | Affiliated with University of Maryland's quantum research institutes.

Richard NicklView profile

Professor

• Mathematical Statistics
• High-dimensional Inference
• Bayesian Nonparametrics
• +3 more

Richard Nickl is a Professor of Mathematical Statistics at the University of Cambridge, affiliated with the Department of Pure Mathematics and Mathematical Statistics (DPMMS) and the Statistical Laboratory. His research focuses on high-dimensional inference, Bayesian nonparametrics, statistics for partial differential equations, and inverse problems. He has held significant grants, including an ERC Advanced Grant (2024–2029) and an EPSRC Programme Grant (2022–2027). His work bridges statistics, probability, and analysis, with contributions to theoretical foundations and computational methods in non-linear inverse problems. Key research interests include Bayesian posterior consistency, statistical inference for diffusions, and polynomial-time algorithms for high-dimensional posteriors. Notable publications include foundational monographs such as Mathematical foundations of infinite-dimensional statistical models (2016), which earned a PROSE Award, and recent advancements in Bayesian nonparametric inference for McKean-Vlasov models (2025). His group organizes workshops, such as the 2024 Statistical Aspects of Non-Linear Inverse Problems conference. Awards: 2017 PROSE Award in Mathematics. Grants: ERC Advanced Grant, EPSRC Programme Grant. Lab/Team: Research Group in Mathematical Statistics at DPMMS, focusing on inverse problems and Bayesian methodology.

Difan ZouView profile

Assistant Professor

• Machine Learning Theory
• Deep Learning Theory
• Optimization Algorithms
• +5 more

Dr. Difan Zou is an Assistant Professor in the Department of Computer Science at the University of Hong Kong's School of Computing and Data Science. He holds a PhD in Computer Science from UCLA and degrees in Applied Physics and Electrical Engineering from the University of Science and Technology of China (USTC). His research focuses on machine learning theory, optimization, and learning structured data such as time-series and graph data, with an emphasis on understanding deep learning's theoretical underpinnings like optimization trajectories and generalization properties. Dr. Zou's academic background includes a B.S. from USTC's School of Gifted Young (Applied Physics) and a M.S. in Electrical Engineering from the same institution. His work bridges theoretical foundations and practical applications, addressing challenges in adversarial robustness, algorithm design for deep neural networks, and explainable machine learning systems in healthcare and finance. His research projects aim to establish rigorous frameworks for deep learning optimization, develop efficient training algorithms, and integrate conventional statistical models with machine learning for improved interpretability. He has received the Bloomberg Data Science Ph.D. Fellowship and has contributed to top-tier conferences like ICML, NeurIPS, and ICLR.

• Real Algebraic Geometry
• Combinatorics
• Convex Optimization
• +3 more

Cynthia Vinzant is an Associate Professor in the Department of Mathematics at the University of Washington. Her research focuses on real algebraic geometry, combinatorics, and convex optimization, with applications to hyperbolic polynomials, determinantal representations, and convex algebraic geometry. She collaborates extensively on projects involving numerical ranges, quasicrystals, and geometric optimization problems. Research Interests: Real algebraic geometry and its connections to combinatorics and optimization Hyperbolic and log-concave polynomials Convex geometry and spectrahedra Applications in matrix analysis and statistical mechanics Her work spans theoretical advances in algebraic geometry and computational methods, including contributions to the study of principal minors, tropical geometry, and phase retrieval problems. Recent publications highlight her focus on Fourier quasicrystals, higher-rank numerical ranges, and combinatorial structures in matroids. Publications: Over 30 peer-reviewed articles, including influential works on quartic curves, determinantal representations, and log-concave polynomials. Grants & Collaborations: Active in interdisciplinary research, with projects supported by NSF and collaborations in algebraic combinatorics and geometric optimization.

Oliver JohnsonView profile

Professor

• Information Theory
• Probability
• Statistics
• +3 more

Professor Oliver Johnson is a faculty member at the School of Mathematics, University of Bristol, UK, where he serves as Head of School and holds the Professor of Information Theory position. His research bridges information theory, probability, and statistics, focusing on entropy convergence, group testing, and fundamental limits in data analysis. Current PhD students: Kieran Morris, Conor Crilly Ex-PhD students: Matt Aldridge, Leonardo Baldassini, Dan Cowley, Vaia Kalokidou, Tom Kealy, Jennifer Chakravarty, Zichen Gui, Chrys Paschou Ex-postdoc: Erwan Hillion His work includes ORCiD profile and collaborations across information theory, cybersecurity, and ecological modeling.

Holden LeeView profile

Assistant Professor

• Machine Learning
• Probability
• Theoretical Computer Science
• +3 more

Holden Lee is an Assistant Professor in the Department of Applied Mathematics and Statistics at Johns Hopkins University, where he joined in 2022. His research focuses on the theoretical foundations of machine learning, probability, and their intersections with theoretical computer science. He explores probabilistic methods in modern machine learning, including deep learning-based generative models and convergence guarantees for sampling algorithms like Markov Chain Monte Carlo. Prior to JHU, he was a postdoc at Duke University and a Simons Fellow at UC Berkeley. He holds a PhD in Mathematics from Princeton University and degrees from MIT and the University of Cambridge. Education: PhD in Mathematics, Princeton University, 2019 MASt in Pure Mathematics, University of Cambridge, 2014 BSc in Mathematics, MIT, 2013 Research Interests: Machine Learning Theory Probabilistic Sampling Methods Generative Models Statistical Learning Theory His work emphasizes theoretical rigor, particularly in understanding the success and limitations of deep learning algorithms and designing efficient sampling techniques beyond classical log-concave settings. Articles Trends: Lee’s recent publications (2022–2024) focus on advancing sampling algorithms for complex distributions, analyzing generative models, and improving convergence guarantees for methods like MCMC and score-based diffusion. His work bridges theory and practice, with applications in multimodal data, text generation, and dynamical systems. Awards: Simons Fellow at UC Berkeley (2021) Advising & Grants: Lee has contributed to projects at NeurIPS and collaborates on research in AI efficiency and theoretical guarantees. He teaches courses on probability and applied mathematics at JHU and Duke. Labs/Teams: His research group focuses on theoretical machine learning and probabilistic methods, with ongoing projects on scalable sampling algorithms and generative model analysis.

• Combinatorics
• Algebraic Combinatorics
• Log-Concave Polynomials
• +13 more

Jonathan Leake is an Assistant Professor in the Department of Combinatorics and Optimization at the University of Waterloo. His research lies at the intersection of combinatorics, optimization, and theoretical computer science, with a focus on log-concave and Lorentzian polynomials and their applications in discrete and continuous settings. Assistant Professor, University of Waterloo (2022–present) Dirichlet Postdoctoral Fellow, TU Berlin (2020–2022) Postdoctoral Fellow, Institut Mittag-Leffler, Stockholm (Spring 2020) Postdoctoral Fellow, KTH, Stockholm (Fall 2019) James H. Simons Fellow, Simons Institute, UC Berkeley (Spring 2019) His research explores the deep connections between algebraic structures and combinatorial phenomena, particularly through polynomial capacity and Lorentzian polynomials. He applies these tools to problems in optimization, sampling, and representation theory. His work often involves developing new algebraic and analytic techniques to tackle longstanding conjectures and algorithmic challenges. The recent publications highlight a consistent focus on Lorentzian polynomials, capacity bounds, and their applications in combinatorics, optimization, and theoretical computer science. Key themes include matroid theory, log-concavity, sampling algorithms, volume approximation, and connections to Lie theory and representation theory. The research spans both theoretical developments and algorithmic applications, often in collaboration with leading researchers in the field. Dirichlet Postdoctoral Fellowship, TU Berlin Postdoc Fellowship in Algebraic and Enumerative Combinatorics, Institut Mittag-Leffler James H. Simons Fellowship, Simons Institute, UC Berkeley Jonathan Leake has advised or collaborated with several researchers, though formal advisees are not listed in the provided text. His work has been supported by prestigious fellowships and collaborations with institutions such as the Simons Institute and TU Berlin. He has taught courses including CO 250: Introduction to Optimization, MATH 239: Introduction to Combinatorics, and CO 739: Lorentzian Polynomials at the University of Waterloo and TU Berlin. While specific lab or research group names are not mentioned, Leake's collaborative work with researchers like Petter Brändén, Nisheeth Vishnoi, and Leonid Gurvits suggests active participation in research teams focused on algebraic combinatorics, optimization, and theoretical computer science. His publicly shared code for sampling from HCIZ densities and verifying positivity in Lie-theoretic contexts indicates an active computational research component.

Hugo Georges Victor LavenantView profile

Assistant Professor

• Optimal Transport
• Calculus of Variations
• Convex Analysis
• +3 more

Hugo Georges Victor Lavenant serves as Assistant Professor in the Department of Decision Sciences at Bocconi University, Milan, where he has held a faculty position since 2020. Previously, he completed a postdoctoral fellowship at the University of British Columbia (2019-2020) under the Pacific Institute of Mathematical Sciences and earned his PhD in Mathematics from Université Paris-Sud (2016-2019) under Filippo Santambrogio's supervision. His academic foundation includes: PhD in Mathematics, Université Paris-Sud (2016-2019) Studies at École Normale Supérieure (2012-2016) covering mathematics, physics, history, and philosophy of science Classes préparatoires in mathematics and physics (2010-2012) Lavenant's research centers on optimal transport theory and its applications across mathematical disciplines. He investigates geometric structures in Wasserstein spaces, develops numerical methods for dynamical optimal transport, and bridges theoretical advances with Bayesian statistics. His work demonstrates particular innovation in trajectory inference for biological data and dependence measures for random measures, connecting pure mathematics with computational statistics. Recent publications reveal accelerating interdisciplinary impact, with 2024-2025 works extending optimal transport to machine learning (kernel methods, variational inference) and data science (opinion dynamics, single-cell analysis). This trajectory shows increasing methodological sophistication in handling measure-valued mappings and non-smooth geometries while maintaining computational tractability. Award recognition includes: Pacific Institute of Mathematical Sciences Postdoctoral Fellowship Lavenant actively mentors early-career researchers through formal advising relationships and collaborative projects. He currently supervises two PhD candidates (George Kanchaveli and Francesco Mascari, co-advised with Marta Catalano) and has guided Master's students including Mathis Hardion and Niccolò Bargellini. His teaching portfolio spans advanced analysis, optimization, and real analysis courses at Bocconi, reflecting his commitment to mathematical rigor in education. He operates within Bocconi's Decision Sciences ecosystem while maintaining international collaborations with researchers at UBC, Université Paris-Sud, and statistical groups worldwide. Current projects focus on entropy-based transport methods and geometric approaches to nonparametric statistics, positioning his work at the intersection of theoretical mathematics and data-driven applications.

Ye HeView profile

Visiting Assistant Professor

• Mathematical Foundations of Artificial Intelligence
• Machine Learning Theory
• Data Science
• +3 more

Ye He serves as a Hale Visiting Assistant Professor in the School of Mathematics at the Georgia Institute of Technology, hosted by Prof. Molei Tao. His research bridges mathematical theory and artificial intelligence, focusing on developing rigorous frameworks for machine learning and data science applications. Education: Ph.D. in Mathematics, University of California, Davis (advised by Prof. Krishna Balasubramanian) Research Interests: Dr. He specializes in the mathematical foundations of artificial intelligence , with particular emphasis on scalable inference methods for complex data distributions. His work addresses fundamental challenges in sampling theory , diffusion-based generative modeling , and stochastic optimization , aiming to establish theoretical guarantees for practical machine learning algorithms. Current investigations focus on heavy-tailed distributions, non-log-concave sampling, and discrete data generation mechanisms. Publication Trends: His 11 most recent publications (2020-2025) reveal a concentrated research program advancing theoretical understanding of sampling algorithms and diffusion models. Work spans top venues including NeurIPS, COLT, and IEEE Transactions on Information Theory, with recurring themes in heavy-tailed distribution sampling, convergence analysis of Langevin dynamics, and optimization of generative architectures. The output demonstrates strong interdisciplinary connections between probability theory, statistics, and machine learning. Scientific Awards: No awards were documented in the source materials. Advising and Grants: The provided information contains no details regarding student supervision, research grants, or funding sources. Teaching responsibilities include undergraduate courses in calculus, linear algebra, and differential equations. Research Environment: Dr. He operates within Georgia Tech's School of Mathematics, collaborating closely with Prof. Molei Tao's research group. His office is located in Skiles 016, and his work contributes to the institution's strengths in mathematical data science and computational theory.

Maben RabiView profile

Professor

• Cyber-Physical Systems
• Networked Control
• Hybrid Systems
• +5 more

Maben Rabi is a Professor at the Department of Information Technology and Communication, University of Southeast Norway. His work focuses on cyber-physical systems, networked control, and hybrid systems with applications in intelligent transportation and robotics. Current projects: CriSp (Research Council) and SafeSmart (KK Foundation). Research keywords: Cyber-Physical Systems, Networked Control, Hybrid Systems, Digital Society, DigiTech. Research Trends : His recent publications emphasize road friction estimation for autonomous vehicles, nonlinear control in relay feedback systems, probabilistic sampling for networked estimation, and packet loss modeling in vehicular networks. These works bridge control theory, cyber-physical systems, and transportation safety. Teaching : Courses include Technology Project (ITD25018) and Digital Control and Cyber-Physical Systems (ITD30019) .

Arturo Jaramillo GilView profile

Researcher

• Stochastic Analysis
• Limit Theorems
• Fractional Brownian Motion
• +4 more

Arturo Jaramillo Gil is a researcher at the Centro de Investigación en Matemáticas (CIMAT), Department of Mathematics. He holds a Ph.D. in stochastic analysis under David Nualart and has conducted postdoctoral research in Luxembourg and Singapore, collaborating with leading researchers in Malliavin calculus and Stein's method. His research focuses on stochastic analysis, limit theorems, fractional Brownian motion, and probabilistic number theory. He has taught courses such as General Topology, Stochastic Calculus, and Stein's Method at institutions like Luxembourg and CIMAT. Key research interests include analysis in Wiener space, local times, random matrices, and applications of Stein's method to number theory. His recent work addresses high-frequency statistics of Lévy processes, non-commutative probability, and quantitative Erdős-Kac theorems. He actively contributes to academic seminars, including the One World Probability and Spanish-speaking probability communities. Jaramillo has authored over 20 publications in top journals like Annals of Applied Probability and Annales de l'Institut Henri Poincaré. His teaching spans graduate and undergraduate levels, emphasizing foundational topics in probability and stochastic processes. He coordinates outreach activities, including schools and workshops on stochastic modeling and probability theory.

Andrej RisteskiView profile

Associate Professor

• Machine Learning
• Statistics
• Theoretical Computer Science
• +5 more

Andrej Risteski is an Associate Professor at the Machine Learning Department of Carnegie Mellon University (CMU) since 2025. He previously held the Norbert Wiener Research Fellow position jointly between the Applied Math Department and IDSS at MIT (2017–2019) after completing his PhD in Computer Science at Princeton University (2012–2017) under Sanjeev Arora . His research focuses on the intersection of machine learning, statistics, and theoretical computer science , emphasizing generative models, representation learning, and out-of-distribution generalization with applications to natural language processing and scientific domains . His recent publications explore edge embeddings in Graph Neural Networks (GNNs) , score matching efficiency , and theoretical foundations of diffusion models . Key contributions include analyzing computational bottlene.com/activities/statistical-and-computational-challenges-in-probabilistic-scientific-machine-learning-sciml/">NSF CAREER Award , DOE Computational Science Graduate Fellowship for Stephen Huan, and co-organizing the COLT workshop on Theory of AI for Scientific Computing . He advises PhD students across Machine Learning, Computer Science, and Mathematics , including Bingbin Liu (Kempner Institute Fellow) and Elan Rosenfeld (Google Research Scientist). Teaching includes Probabilistic Graphical Models and Advanced Deep Learning at CMU, plus Applied Mathematics at MIT. His work is supported by NSF, DoD , and OpenAI Superalignment grants. Education : PhD in Computer Science (Princeton), BSc in Computer Science (Princeton) Current Positions : Associate Professor, CMU Machine Learning Department Former Positions : Norbert Wiener Fellow, MIT IDSS & Applied Mathematics Research Areas : Generative Models (GANs, Diffusion Models) Representation Learning Out-of-Distribution Generalization Neural Language Models AI for Scientific Applications Sampling and Optimization Algorithms Scientific Awards : NSF CAREER Award (2023) Google Research Award (2024) Amazon Research Award (2022) OpenAI Superalignment Grant (2023) Recent Talks (2023–2025): "Architectural Nuances and Benchmark Gaps in Scientific ML" (UC Berkeley, 2025) "The Statistical Cost of Score-Based Losses" (Simons Institute Boot Camp, 2024) "Neural Networks for PDEs" (ETH Zurich, 2024) "Discernible Patterns in Transformers" (Theory of Interpretable AI, 2024) He leads a research group producing work at the interface of computational complexity and graph learning , with empirical validation on topological bottlenecks and hub node dynamics . Current projects include ICML 2025 paper on edge embeddings in GNNs and COLT 2025 workshop on AI for Scientific Computing co-organized with MIT, Duke, and ETH Zurich collaborators.

Avetik KaragulyanView profile

Researcher

• Statistical Sampling
• Optimization
• Machine Learning
• +3 more

Avetik Karagulyan is a CNRS Research Scientist at L2S (Laboratory of Signals and Systems) affiliated with CentraleSupélec in France. He holds a PhD from CREST (Center for Research in Economics and Statistics), Paris, under Prof. Arnak Dalalyan, and an MSc in Mathematics, Vision, Learning from ENS Paris-Saclay. His research focuses on statistical sampling methods, optimization, and their applications in machine learning, particularly federated learning and non-convex optimization. He has contributed to advancements in Langevin Monte Carlo algorithms, variance reduction techniques, and distributed optimization frameworks. Education: PhD, Statistics, CREST, Paris (2021) MSc, Mathematics, Vision, Learning, ENS Paris-Saclay (2018) BSc, Mathematics and Mechanics, Yerevan State University (2017) Research Interests: He investigates sampling algorithms (e.g., Langevin Monte Carlo), federated learning, non-convex optimization, and their theoretical guarantees. His work bridges stochastic processes, optimization theory, and machine learning applications. Labs/Teams: He is part of the L2S lab, contributing to groups like MODESTY (Modeling for Control of Dynamic Systems) and SYCOMORE (Robust Control of Complex Systems). His research aligns with transversal axes in energy and industry innovation at Paris-Saclay. Grants & Advising: No explicit grants or advisees listed, though his collaborative projects suggest involvement in funded research initiatives.

Charles R DossView profile

Associate Professor

• Nonparametric Inference
• Shape-Constrained Estimation
• Continuous Treatment Effects
• +7 more

Charles R Doss is an Associate Professor in the Department of Statistics at the University of Minnesota, Twin Cities, within the College of Science and Engineering. His research is centered on nonparametric inference, shape-constrained estimation, and continuous treatment effects, with applications in public health and precision medicine. He has led multiple funded research projects from the National Science Foundation and the Department of Health. Research Interests: Dr. Doss specializes in nonparametric methods, particularly under shape constraints such as convexity and monotonicity. His work includes developing theory and methodology for optimal treatment regimes, continuous treatment effects, and robust inference. Applications span public health, including wastewater surveillance for pathogens like SARS-CoV-2, and statistical learning in high-dimensional settings. The recent publications show a strong trend in causal inference, robust statistical methods, and interdisciplinary applications, particularly in public health and machine learning. His work often involves theoretical development with practical implementation, as seen in projects on wastewater surveillance and multivariate regression models. Scientific Awards: No specific awards listed in the provided text. Advising and Grants: Dr. Doss has been the Principal Investigator on three National Science Foundation grants and a Co-Investigator on a Department of Health project related to wastewater surveillance. His funding history from 2017 to 2026 reflects sustained support for methodological and applied statistical research. While no students are listed, his role as PI suggests active mentorship and research leadership. Labs and Teams: He collaborates with interdisciplinary teams, including public health officials and researchers in virology and environmental science, particularly through the wastewater surveillance project. His network includes researchers from various institutions and disciplines, indicating a collaborative research environment.

• measure theory
• Gaussian measures
• measures on infinite-dimensional spaces
• +4 more

Egor Dmitrievich Kosov is an Associate Professor at the Faculty of Computer Science of the National Research University Higher School of Economics (HSE), where he has been working since 2016. He also serves as a Senior Research Fellow at the International Laboratory of Stochastic Algorithms and Multidimensional Data Analysis within HSE's Institute of Artificial Intelligence and Digital Sciences. Additionally, he holds positions as Senior Researcher at the Steklov Mathematical Institute's Department of Function Theory and Junior Researcher at the Laboratory of Multidimensional Approximation and Applications. Dr. Kosov earned his Candidate of Physical and Mathematical Sciences degree from Lomonosov Moscow State University in 2018, where he also completed postgraduate studies specializing in Mathematics and Mechanics with a qualification as Researcher. His research focuses on measure theory , particularly Gaussian measures , measures on infinite-dimensional spaces , logarithmically concave measures , and measurable polynomials . Kosov's work bridges theoretical mathematics with applications in stochastic analysis, exploring the regularity properties of distributions and developing discretization techniques for functional norms. His research has significant implications for understanding complex probabilistic structures in high-dimensional spaces. Analysis of Kosov's recent publications reveals a strong focus on polynomial mappings of random variables, particularly Gaussian and log-concave distributions. A significant portion of his research addresses discretization problems—developing methods to approximate continuous mathematical structures through discrete sampling. His publications demonstrate growing recognition in the mathematical community, with appearances in prestigious journals across multiple subfields of mathematical analysis. Letter of gratitude from the First Vice-Rector of HSE (March 2023) Letter of Gratitude from the Faculty of Computer Science at HSE (September 2019) Bonus for publication in List A journals (2023-2024) Multiple bonuses for international peer-reviewed publications (2019-2023) Best Teacher award (2018) Moscow Mathematical Society award (2021) At HSE, Kosov teaches Mathematical Analysis, Probability Theory, and Functional Analysis to undergraduate students in the Applied Mathematics and Computer Science program across both the Faculty of Computer Science and the Faculty of Economic Sciences. His teaching spans multiple academic years (2020-2023), demonstrating his commitment to education alongside research. Dr. Kosov is actively involved in research teams including the International Laboratory of Stochastic Algorithms and Multidimensional Data Analysis at HSE and the Laboratory of Multidimensional Approximation and Applications. His work connects with the broader mathematical community through collaborations with researchers such as V.I. Bogachev, V.N. Temlyakov, and others, contributing to Russia's strong tradition in mathematical analysis and probability theory.