Find Academic Supervisors

• Reinforcement Learning
• Learning in Games
• Applied Probability
• +2 more

Zaiwei Chen is an Assistant Professor in the Edwardson School of Industrial Engineering at Purdue University. His research focuses on developing theoretical foundations for sequential decision-making under uncertainty, particularly in reinforcement learning, multi-agent systems, and optimization. He leads projects on data-efficient algorithms with applications in control and game theory. He holds a Ph.D. in Machine Learning and dual M.S. degrees in Mathematics and Operations Research from Georgia Institute of Technology, and a B.S. in Electrical Engineering from Zhejiang University. His research bridges applied probability, machine learning, and optimization to create robust algorithms for complex systems. Recent work emphasizes convergence guarantees in multi-agent reinforcement learning and scalable solutions for high-dimensional problems. Chen's publications demonstrate a consistent focus on theoretical guarantees for reinforcement learning algorithms, particularly in stochastic and game-theoretic settings. Key trends include Lyapunov stability frameworks, finite-sample analysis, and methods to overcome computational bottlenecks like the "curse of dimensionality." Awards include: Solberg Academic Excellence Scholarship PIMCO Postdoctoral Fellowship in Data Science (2022) Sigma Xi Best Ph.D. Thesis Award Runner-up for SIGMETRICS Doctoral Dissertation Award He actively recruits PhD students to work on reinforcement learning theory and maintains collaborations with Caltech and Georgia Tech. Future work includes scalable multi-agent learning frameworks and real-world applications in industrial systems.

Ruqi ZhangView profile

Assistant Professor

• Machine Learning
• Deep Learning
• Probabilistic Methods
• +5 more

Ruqi Zhang is an Assistant Professor in the Department of Computer Science at Purdue University. Previously, she was a postdoctoral fellow at the Institute for Foundations of Machine Learning, UT Austin (2021-2022), and earned her PhD in Statistics from Cornell University (2016-2021). Her research focuses on scalable probabilistic methods for machine learning, including alignment of foundation models, uncertainty quantification, and Bayesian deep learning. She has received awards such as the Ross-Lynn Research Scholar Fund and ICML Best Reviewer recognition. Education: PhD in Statistics, Cornell University (2021) MS in Computer Science, Cornell University (2021) Bachelor of Science in Mathematics, Renmin University of China (2012-2016) Research Interests: Trustworthy AI: Safety of LLMs/VLMs, alignment mechanisms Probabilistic Inference: Bayesian methods, MCMC, variational inference Generative Models: Diffusion models, energy-based models Uncertainty Estimation: Calibration, out-of-distribution detection Notable Contributions: Developed the Discrete Langevin Sampler for high-dimensional discrete spaces Pioneered Low-Precision SGLD for efficient Bayesian neural networks Designed DP-Fast MH for privacy-preserving Bayesian inference Teaching: CS57800 - Statistical Machine Learning (2022-Present) CS37300 - Data Mining and Machine Learning (2024) CS59200 - Probabilistic Machine Learning (2022)

• Mathematical Physics
• Probability Theory
• Random Matrix Theory
• +5 more

Gaultier Lambert is an Associate Professor at the Department of Probability, Mathematical Physics and Statistics, KTH Royal Institute of Technology. His research focuses on the intersection of probability theory, mathematical physics, and random matrix theory, with particular emphasis on determinantal processes, log-correlated fields, and quantum statistics. He holds a PhD and has an extensive publication record in high-impact journals. Key research areas include fluctuations in free fermionic systems, multiplicative chaos, and universality in random matrix ensembles. His work explores topics such as characteristic polynomials of random matrices, law of large numbers for Coulomb gas potentials, and quantum statistics transmutation via magnetic flux attachment. Recent publications (2021–2025) emphasize asymptotic analysis of eigenvalue fluctuations, universality in semiclassical systems, and stochastic processes in high-dimensional spaces. Lambert’s contributions bridge theoretical probability with applications in quantum physics and statistical mechanics. No scientific awards or grants are explicitly listed in the provided texts. He advises no listed students and is affiliated with the Lindstedtsvägen 25 research group at KTH.

Haotian XuView profile

Assistant Professor

• Nonparametric Estimation
• High-dimensional Inference
• Change Point Detection
• +5 more

Haotian Xu is a Harrison Early Career Assistant Professor in the Department of Statistics at the University of Warwick. His research focuses on nonparametric estimation in high-dimensional settings, change point detection, and inference under temporal dependence and contamination. He holds a Ph.D. from the University of Geneva (2021) and an MSc from the University of Illinois at Urbana-Champaign (2015). His postdoctoral work involved collaborations at institutions like Pennsylvania State University and Université Catholique de Louvain. Key research areas include robust statistical methods, wavelet-based inference, and applications in sensor calibration and functional data analysis. He has developed R packages such as 'changepoints' and 'FragmentCP' for change point detection. Teaching responsibilities include Bayesian Forecasting and Intervention at Warwick and courses in statistical modeling at Penn State and the University of Geneva. His publications span high-impact journals like the Annals of Statistics and IEEE Transactions, addressing challenges in time series analysis, multivariate modeling, and computational statistics. Current projects emphasize scalable inference for large datasets and fragmented functional data analysis.

• Numerical Analysis
• Partial Differential Equations
• Differential Geometry
• +4 more

Hanne Hardering is a researcher at the Department of Numerical Mathematics, Faculty of Mathematics, Technische Universität Dresden. She holds a PhD (Dr. rer. nat.) from Freie Universität Berlin (2015) and a Diplom in Mathematics (2010). Her research focuses on the numerical analysis of partial differential equations on surfaces and Riemannian manifolds, with expertise in finite element methods, geometric numerical techniques, and error analysis. Her doctoral work, supervised by Prof. Ralf Kornhuber and Prof. Klaus Ecker, centered on discretization error bounds for geodesic finite elements. Current research includes subproject leadership in DFG Research Unit 3013 on vector/tensor-valued surface PDEs, focusing on symmetry, length, and tangential constraints. Key contributions span surface Stokes equations, geometric finite elements, and manifold-valued spline approximations. Publications emphasize rigorous mathematical analysis of numerical methods, with applications in geometric modeling and differential geometry. Collaborations include work with renowned institutions and researchers such as SIAM, Oberwolfach Reports, and Springer’s Handbook of Variational Methods. Her work bridges numerical analysis with geometric theory, advancing computational tools for complex PDE systems.

Michelle MichelleView profile

Visiting Assistant Professor

• Numerical Methods for Wave Propagation
• Wavelet Methods for PDEs
• Scientific Machine Learning
• +3 more

Michelle Michelle is a Golomb Visiting Assistant Professor of Mathematics at Purdue University, mentored by Jianlin Xia and Haizhao Yang. She holds a PhD in Applied Mathematics from the University of Alberta (2022), advised by Bin Han and Yau Shu Wong. Her research focuses on numerical methods for wave propagation, elliptic interface problems, wavelet methods in PDEs and data science, and scientific machine learning. She has taught courses including MA 303 and MA 266 at Purdue and held teaching roles at the University of Alberta. Her research explores advanced numerical techniques for solving Helmholtz equations and electromagnetic scattering problems, with notable contributions to wavelet-based Galerkin methods and stable fast multipole algorithms. Recent work emphasizes high-order accuracy, stability analysis, and applications in computational physics. Michelle has presented at major conferences such as SIAM Applied Linear Algebra (2024) and SIAM Great Lakes Section (2022), focusing on numerical methods for wave equations and algorithmic stability. She has also contributed to workshops like the NSF Computational Mathematics PI Meeting (2024) and ICERM Modern Applied and Computational Analysis (2023). Her publications span journals like SIAM Journal on Numerical Analysis and Applied and Computational Harmonic Analysis.

Ryan TibshiraniView profile

Professor

• High-Dimensional Statistics
• Nonparametric Estimation
• Distribution-Free Inference
• +5 more

Ryan Tibshirani is a Professor of Statistics at the University of California, Berkeley, and Principal Investigator in the Delphi group. Previously, he was faculty at Carnegie Mellon University (2011–2022). He holds a Ph.D. in Statistics (2011) and a B.S. in Mathematics (2007) from Stanford University. His research focuses on high-dimensional statistics, nonparametric methods, distribution-free inference, and machine learning, with applied work in computational epidemiology, particularly tracking and forecasting epidemics like influenza and COVID-19. He has contributed to open-source tools like the conformalInference R package for predictive inference. Education: Ph.D. in Statistics, Stanford University (2011); B.S. in Mathematics, Stanford University (2007). Professional service includes Editor-in-Chief roles for Foundations and Trends in Machine Learning and Statistics, and membership in the Institute of Mathematical Statistics Council. Research interests span theoretical and applied statistics, including convex optimization, numerical methods, and collaborative efforts in public health forecasting. His work on the Delphi group has advanced real-time epidemic monitoring via sensor fusion and probabilistic forecasting. Recent projects address challenges in estimating time-varying epidemic severity and improving predictive model calibration under distribution shifts. Key contributions include unifying conformal prediction theories, developing trend filtering methods for lattice data, and advancing understanding of cross-validation in overparameterized models. His software tools emphasize reproducibility and scalability for large-scale statistical tasks.

David BleiView profile

Professor

• Probabilistic Topic Models
• Bayesian Nonparametric Methods
• Approximate Posterior Inference
• +5 more

David Blei is a Professor of Computer Science and Statistics at Columbia University, holding dual appointments in Columbia Engineering and the Faculty of Arts and Sciences. He joined Columbia in 2014 after serving as an Associate Professor of Computer Science at Princeton University. His research focuses on probabilistic topic models, Bayesian nonparametric methods, and approximate posterior inference, with applications in text, images, social networks, and scientific data. Education: Bachelor’s in Computer Science and Mathematics, Brown University (1997) PhD in Computer Science, University of California, Berkeley (2004) Research Interests: Probabilistic modeling and Bayesian methods Machine learning applications in social and biological sciences Causal inference and fairness in AI Generative models and representation learning Awards: Sloan Fellowship (2010) Office of Naval Research Young Investigator Award (2011) Presidential Early Career Award for Scientists and Engineers (2011) Blavatnik Faculty Award (2013) Advising & Grants: Professor Blei has advised numerous students and led interdisciplinary research projects, though specific grant details are not explicitly listed. His work bridges theoretical foundations with practical applications in healthcare, economics, and social science. Labs & Affiliations: Affiliated with Columbia’s Foundations of Data Science, Computing Systems for Data-Driven Science, and Computational Social Science centers, advancing interdisciplinary data science initiatives.

Timothy B. ArmstrongView profile

Professor

• Econometrics
• Statistics
• Applied Economics
• +4 more

Timothy B. Armstrong is a Professor of Economics at the University of Southern California (USC), affiliated with the Department of Economics within the USC Dornsife College of Letters, Arts and Sciences. His research focuses on econometric theory, statistical inference, and applied economics, emphasizing robust estimation, treatment effects analysis, and moment inequality models. Armstrong has contributed extensively to methodologies for confidence intervals, hypothesis testing, and model misspecification adjustments. His work spans econometric topics such as optimal estimation of treatment effects under unconfoundedness, sensitivity analysis in approximate moment condition models, and adaptive testing in nonparametric regression. He has developed software tools (e.g., R and Stata packages) for robust empirical Bayes methods and bandwidth adjustments. Armstrong’s recent research addresses misspecification adaptation, panel data analysis, and false discovery rate adjustments in multiple testing scenarios. Publications in top journals like Econometrica and Quantitative Economics reflect his expertise in econometric theory and applications. His grants and collaborations emphasize methodological advancements in statistical decision theory and empirical practice.

Robert LoftinView profile

Lecturer

• Ad Hoc Human-AI Cooperation
• Human-AI Alignment
• Human-in-the-loop Machine Learning
• +6 more

Dr. Robert Loftin is a Lecturer in Machine Learning at the University of Sheffield’s School of Computer Science. His research focuses on Ad Hoc Human-AI Cooperation, Human-AI Alignment, and Human-in-the-loop Machine Learning, with expertise in Deep Reinforcement Learning and Multi-Agent Systems. He holds a PhD from North Carolina State University (2019) and a Bachelor’s from Georgia Tech (2011). Postdoctoral work includes roles at Microsoft Research Cambridge and TU Delft, exploring AI applications in gaming and multi-agent cooperation. His research interests span AI ethics, human-robot interaction, and games, with a strong emphasis on practical applications of interactive learning. Recent work includes advancements in entropy-based coordination for multi-agent systems (2023–2025) and theoretical studies on cooperation in socially rational agent populations. He contributes to the Machine Learning research group and has published extensively in top venues like NeurIPS, AAMAS, and AAAI. Publications highlight innovations in curriculum design, exploration strategies, and adaptive feedback mechanisms. His work bridges theoretical foundations and real-world applications, particularly in cooperative and competitive multi-agent environments. Current projects explore safe team coordination and scalable strategies for high-dimensional state spaces.

• Applied Signal Processing
• Inverse Problems
• Greedy Algorithms
• +5 more

Florian Bossmann is an Associate Professor at the College of Mathematics, Harbin Institute of Technology (HIT), specializing in Applied Signal Processing with a focus on algorithms and applications. His research encompasses inverse problems, greedy algorithms, sparsity, and compressed sensing, with applications in seismic exploration, ptychography, and video processing. He holds a PhD in Mathematics from the University of Göttingen (2013) and a Diplom in Mathematics from the University of Duisburg-Essen (2009). Current projects include NSFC-funded seismic data interpolation and a start-up grant for applied signal processing research. He teaches courses like 'Signal and Image Processing' and 'Calculus for Civil Engineering'. Supervising Master/PhD students in signal processing, he emphasizes collaboration and innovation. His lab, the ASP Group, explores cutting-edge methods in multidimensional data reconstruction and algorithm design. Prominent publications focus on impedance inversion, neural network applications in geoscience, and object reconstruction techniques. He has led collaborative research initiatives with institutions like the Fraunhofer Institute and the Helmholtz Center for Environmental Health.

Sühan AltayView profile

Researcher

• Financial Mathematics
• Quantitative Finance
• Stochastic Processes
• +5 more

Sühan Altay is a researcher affiliated with the Institute for Statistics and Mathematics at Vienna University of Economics and Business (WU Wien) . His work focuses on Financial Mathematics , Quantitative Finance , and Stochastic Processes , with applications to portfolio optimization, high-frequency trading, and partial information models. He has collaborated extensively with researchers like Prof. Zehra Eksi-Altay and Prof. Kenneth Colaneri. His research spans topics such as optimal trading strategies under uncertainty, market microstructure analysis, and the valuation of complex financial instruments. Notable contributions include studies on dark pools, pairs trading, and regime-switching models. His publications appear in journals like SIAM Journal on Financial Mathematics , International Journal of Theoretical and Applied Finance , and Annals of Operations Research . He holds a Dr.rer.nat. (PhD) in Statistics and Mathematics and has contributed to teaching materials, including lecture notes on stochastic differential equations. No awards or grants are explicitly mentioned in the provided texts.

Yang LiuView profile

Assistant Professor

• Theoretical Computer Science
• Graph Algorithms
• Optimization
• +4 more

Yang P. Liu is an Assistant Professor in the Computer Science Department at Carnegie Mellon University. Previously, he was a Postdoctoral Member at the Institute for Advanced Study and earned his PhD from Stanford University under the supervision of Aaron Sidford. His research focuses on theoretical computer science and mathematics, emphasizing graph algorithms, optimization, high-dimensional geometry, and additive combinatorics. He has received notable awards including the A.W. Tucker Prize and Google PhD Fellowship, alongside multiple best paper recognitions at major conferences like FOCS, STOC, and ITCS. Education: PhD in Computer Science from Stanford University (2023); BS from MIT (2018). Research Interests: Graph Algorithms Optimization (especially convex and high-dimensional) Algorithmic Techniques in Additive Combinatorics Geometric and Structural Aspects of Computation Teaching: Currently instructing CS 15-759: A Principled Approach to Optimization (Spring 2025), covering topics like gradient descent, interior-point methods, and sparsification techniques. Course emphasizes rigorous mathematical foundations. Awards: Recognized for contributions to optimization theory and algorithmic complexity. His work bridges discrete mathematics and continuous optimization paradigms.

Matias QuirozView profile

Senior Lecturer

• Computational Statistics
• Bayesian Methods
• Machine Learning
• +4 more

Matias Quiroz is a Senior Lecturer at the University of Technology Sydney (UTS) in the School of Mathematical and Physical Sciences. He joined UTS in July 2023 after previously serving as a Lecturer (2019–2022) and Senior Lecturer (2022–2023) at Stockholm University. His expertise lies in computational statistics, Bayesian methods, and machine learning. He holds a Ph.D. from Stockholm University (2015) and an M.Sc. in Engineering Mathematics from Lund University (2009). Research focuses on developing efficient MCMC algorithms for large datasets and variational approximations for high-dimensional models. He has contributed to areas like subsampling MCMC, spectral analysis of time series, and Bayesian inference for complex models. Quiroz is also an Associate Editor for Computational Statistics and Data Analysis and Econometrics and Statistics . Teaching responsibilities include courses such as Machine Learning: Mathematical Theory and Applications and Programming for Data Analysis. He has supervised students at various academic levels and has held editorial and leadership roles, including serving as the Young Stats representative for the NSW Branch of the Statistical Association of Australia since 2025. His work bridges Bayesian statistics with machine learning, emphasizing scalable computational methods. Notable research themes include high-dimensional state space models, dynamic linear regression, and algorithmic innovations for big data problems.

Yue LuView profile

Professor

• Applied Mathematics
• Control Theory and Stochastic Systems
• Data Science
• +5 more

Yue Lu is the Gordon McKay Professor of Electrical Engineering and Applied Mathematics at Harvard University, serving as Faculty Director of Graduate Studies. His research spans applied mathematics, control theory, machine learning, and signal processing, with a focus on high-dimensional data analysis and algorithmic foundations. He leads the Signal and Information Processing lab in Maxwell Dworkin 113. Notable recognitions include being named a Harvard College Professor (2024) and achieving tenure in 2019. His work addresses topics like random matrix theory, optimization in machine learning, and statistical signal processing. Recent contributions include studies on neural networks, kernel methods, and phase retrieval algorithms. He has published extensively on the theoretical underpinnings of modern learning systems, with a particular emphasis on universality principles and asymptotic analysis. Research Highlights: Developed frameworks for analyzing approximate message passing algorithms Advanced theories of in-context learning and feature learning dynamics Contributed to understanding phase transitions in high-dimensional estimation problems Explored optimal regularization strategies for sparse regression Awards: Harvard College Professor (2024) Full Tenure in Electrical Engineering (2019) His lab focuses on bridging theory and applications in signal processing and AI, with projects ranging from imaging systems to brain network analysis. Ongoing work explores the statistical physics of learning and scalable algorithms for large-scale inference problems.