Find Academic Supervisors

Wenting ZhengView profile

Assistant Professor

• Secure Systems
• Applied Cryptography
• Privacy-Preserving Computation
• +4 more

Wenting Zheng is an Assistant Professor in the Computer Science Department at Carnegie Mellon University (CMU), with a courtesy appointment in the Electrical and Computer Engineering Department. She co-founded Opaque Systems and serves as a core faculty member at CyLab Security and Privacy Institute. Ph.D. in Electrical Engineering and Computer Science (EECS) from UC Berkeley M.Eng. and Bachelor’s degrees from MIT under Barbara Liskov Her research focuses on system security and applied cryptography , particularly systems enabling “sharing without showing.” Key areas include secure cloud computation, collaborative privacy-preserving analytics, and practical cryptographic frameworks for machine learning. Recent work emphasizes encrypted AI (e.g., Cinnamon), secure multi-party computation (e.g., Silph), and private information retrieval (e.g., PIANO). Notable scientific honors include the Berkeley Fellowship (2014-2016) , IBM Research Fellowship (2017-2018) , and the USENIX Security 2021 Distinguished Paper Award . She has advised numerous Ph.D. and Master’s students, including collaborators at CMU and UC Berkeley. Teaching: Distributed Systems, Secure Computer Systems, Cryptosystems: Theory and Practice Research grants from NSF, AWS, Cisco, Google, Samsung, and CMU CyLab Co-founder of DARE, a diversity-focused research mentorship program

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.

Charlie GarrodView profile

Academic

• distributed database systems
• computer science education
• teaching assistant mentorship
• +6 more

Charlie Garrod is an Associate Teaching Professor in the Software and Societal Systems Department within Carnegie Mellon University's School of Computer Science. His academic career focuses primarily on undergraduate computer science education and related areas such as teaching assistant and faculty mentorship. Institution: Carnegie Mellon University School: School of Computer Science Department: Software and Societal Systems Department Position: Associate Teaching Professor Dr. Garrod received his B.S. in Computer Science from Harvey Mudd College in 2001 and completed both his M.S. and Ph.D. in Computer Science at Carnegie Mellon University in 2006 and 2008, respectively. His educational background laid the foundation for his expertise in distributed database systems and software engineering education. His research interests center around computer data management systems, with particular emphasis on the performance, scalability, and power management of highly scalable distributed systems. As a teaching professor, his research program is intentionally focused on undergraduate and Master's student research projects rather than large-scale independent research. His work bridges theoretical computer science with practical applications in transportation information systems, mobile location services, and database scalability. Dr. Garrod's publication history reveals a strong trajectory in distributed systems and database technologies, with recent work shifting toward educational topics such as mentoring teaching assistants. His publications span prestigious venues including ACM Transactions on Algorithms, VLDB, ICDE, and SIGCHI, with his work on the Tiramisu transportation system earning a CHI 2011 Honorable Mention. His research demonstrates consistent contributions to database caching, query optimization, and consistency management for web applications. CHI 2011 Honorable Mention for 'Field Trial of Tiramisu: Crowd-Sourcing Bus Arrival Times to Spur Co-Design' As an educator, Dr. Garrod has mentored numerous students through formal courses and undergraduate research projects. He has developed and taught a wide range of courses including software design and engineering, algorithms and data structures, theoretical computer science, distributed systems, and databases. His teaching philosophy emphasizes practical application of theoretical concepts, with a focus on preparing students for real-world software engineering challenges. He has been actively involved in developing pedagogical approaches for computer science education, particularly in the mentorship of teaching assistants. Dr. Garrod maintains an active teaching schedule, currently instructing courses such as 15-210 Parallel and Sequential Data Structures and Algorithms, 17-480/17-780 API Design, and 07-070 Teaching Techniques for Computer Science. His extensive teaching portfolio demonstrates deep commitment to computer science education across multiple institutions and course levels.

• Trustworthy AI/ML
• Causal ML
• Out-of-distribution Robustness
• +4 more

David I. Inouye is an Assistant Professor at Purdue University's Elmore Family School of Electrical and Computer Engineering (ECE), where he conducts research on trustworthy machine learning methods that are robust to imperfect distributional and computational assumptions. His work bridges the gap between theoretical foundations and practical applications in AI systems. Dr. Inouye's educational background includes: PostDoc in Machine Learning (2019) from Carnegie Mellon University under Prof. Pradeep Ravikumar PhD in Computer Science (2017) from The University of Texas at Austin under Profs. Inderjit Dhillon and Pradeep Ravikumar MS in Computer Science (2015) from The University of Texas at Austin BS in Electrical Engineering (2012) from Georgia Institute of Technology BA in Natural Sciences (2011) from Covenant College Dr. Inouye's research focuses on developing trustworthy AI systems through multiple interconnected threads. His primary research vision centers on creating machine learning methods that maintain robust performance even when faced with distributional shifts or computational constraints. Trustworthy AI/ML forms the foundation of his work, with particular emphasis on Causal ML approaches to understand and mitigate robustness issues. He investigates how ML explanations relate to model robustness, exploring whether interpretability can enhance reliability. Another significant strand examines Robust Collaborative Learning on dynamic networks of edge devices, addressing the challenges of distributed AI systems. His work on Distribution Shift and Robustness tackles the critical problem of models failing when deployed in environments different from training conditions. Additionally, he explores Fairness in machine learning, viewing it as a specific form of robustness to sensitive attributes. Dr. Inouye's recent publications (2022-2025) reveal a strong focus on causal approaches to robustness, with approximately 40% of his work connecting counterfactual reasoning to distribution shift problems. His research shows a clear trajectory toward practical implementations of theoretically grounded methods, with increasing emphasis on collaborative and federated learning settings. The interdisciplinary nature of his work is evident in publications spanning computer vision (25%), graph neural networks (15%), and fundamental machine learning theory (60%). Dr. Inouye has received recognition for his research, including a Spotlight paper at ICLR 2024 (5% acceptance rate) for his work on "Benchmarking Algorithms for Federated Domain Generalization." As an educator and mentor, Dr. Inouye has taught multiple iterations of ECE 47300 (Introduction to Artificial Intelligence) and ECE 57000 (Artificial Intelligence), as well as ECE 20875 (Python for Data Science). His research has been supported by significant funding from the National Science Foundation (NSF) , the Army Research Laboratory (ARL) , and the Office of Naval Research (ONR) . These grants have enabled his team to pursue ambitious research questions at the intersection of theory and practice in trustworthy machine learning. Dr. Inouye leads the Inouye Lab at Purdue University, which focuses on developing theoretically sound yet practical approaches to trustworthy machine learning. The lab maintains active collaborations with researchers at Carnegie Mellon University, The University of Texas at Austin, and industry partners working on edge computing and robust AI systems. Current projects include developing methods for robust collaborative learning across distributed edge devices and creating causal frameworks for understanding and mitigating distribution shifts in real-world applications.

• Machine Learning
• Differential Privacy
• Reinforcement Learning
• +3 more

Yu-Xiang Wang is an Associate Professor at the Halıcıoğlu Data Science Institute and the Department of Computer Science and Engineering at UC San Diego. Previously, he was an Assistant Professor at UC Santa Barbara from 2018-2023, where he founded the S2ML lab and co-founded the Center for Responsible Machine Learning. He earned his Ph.D. from Carnegie Mellon University's Machine Learning Department and worked at Amazon AI before joining academia. Education: Ph.D. in Machine Learning, Carnegie Mellon University Research Focus: His work spans machine learning theory, differential privacy, reinforcement learning, and practical applications in healthcare and financial markets. His lab, S2ML, focuses on designing efficient ML algorithms with provable guarantees and addressing societal challenges like data privacy and abuse prevention. Recent Research Trends: His recent publications focus on neural network theory, differential privacy, reinforcement learning, and generative AI watermarking. Key themes include understanding the theoretical limits of deep learning, developing privacy-preserving algorithms, and ensuring the robustness of AI systems. Grants & Awards: NSF CAREER Award NSF SCALE MoDL Award NSF RI Award NSF III Award Students Advised: He has successfully advised 7 Ph.D. graduates including Ming Yin, Kaiqi Zhang, Dheeraj Baby, Rachel Redberg, Yuqing Zhu, Chong Liu, and Xuandong Li. Current Position: Actively recruiting motivated students and postdocs for his S2ML lab at UC San Diego.

Gerard CornuejolsView profile

Professor

• Integer Programming
• Combinatorial Optimization
• Packing and Covering
• +4 more

Gerard Cornuejols is a Professor at Carnegie Mellon University's Tepper School of Business, where he maintains an active research program in integer programming and combinatorial optimization. His office is located in Tepper School Room 4107 at 5000 Forbes Avenue, Pittsburgh, PA 15213. Professor Cornuejols' research focuses on integer programming and combinatorial optimization, particularly packing and covering problems. His work bridges theoretical mathematics with practical applications in financial optimization and network design. He has made significant contributions to polyhedral combinatorics, developing fundamental insights into the structure of integer programs and their relaxations. His research often explores the connections between graph theory, linear programming, and discrete optimization, with applications ranging from financial portfolio management to network flow problems. His publication record demonstrates consistent high-impact contributions across both theoretical and applied optimization. Recent work shows a strong trend toward dyadic programming, fractional packings, and the study of ideal clutters, while maintaining connections to practical financial applications. The research spans pure combinatorial theory to applied financial optimization, reflecting his ability to connect abstract mathematical structures with real-world problems. Fulkerson prize 2000 for best paper in Discrete Mathematics SIAM Outstanding Paper Prize 2004 Most frequently cited paper published in Discrete Optimization 2005-2010 Professor Cornuejols has established himself as a leading figure in optimization through his influential books, extensive publication record, and collaborative research with prominent mathematicians including Michele Conforti, Giacomo Zambelli, and Ahmad Abdi. His work on the strong perfect graph theorem and ideal clutters has shaped modern combinatorial optimization theory.

Zico KolterView profile

Professor

• Artificial Intelligence
• Machine Learning
• Adversarial Machine Learning
• +5 more

Zico Kolter is a Professor and Department Head of the Machine Learning Department at Carnegie Mellon University's School of Computer Science. He also serves on the Board of Directors at OpenAI, chairs its safety and security committee, and holds roles at Gray Swan AI and Robert Bosch, LLC. His research focuses on AI safety, adversarial robustness, LLM security, and computational methods for energy systems. Kolter holds a PhD in Computer Science from Stanford University (2010) and has received accolades including the DARPA Young Faculty Award and Sloan Fellowship. His work addresses challenges in machine learning, optimization, and control systems, with applications to sustainability, robotics, and energy grids. Notable contributions include advancements in adversarial defense mechanisms, implicit models, and energy disaggregation. Kolter teaches courses such as Graduate Artificial Intelligence and Deep Learning Systems, and leads a research group producing influential work in NeurIPS, ICML, and other top venues. Scientific awards include multiple best paper recognitions at NeurIPS, ICML, AISTATS, IJCAI, KDD, and PESGM. His advising spans students like Victor Akinwande and Andy Zou, focusing on topics from causal discovery to LLM security. Kolter's contributions extend to software tools like TorchDEQ and frameworks for computational sustainability, emphasizing both theoretical rigor and real-world impact.

• Machine Learning
• Natural Language Processing
• Natural Language Understanding
• +3 more

Abulhair Saparov is an Assistant Professor of Computer Science at Purdue University , where he focuses on statistical machine learning applications in natural language processing (NLP), reasoning, and symbolic/neuro-symbolic systems. Prior to Purdue, he was a postdoctoral researcher at the Center for Data Science at New York University under Professor He He. He holds a Ph.D. and M.S. in Machine Learning from Carnegie Mellon University (advised by Professor Tom Mitchell) and a B.S.E. in Computer Science from Princeton University with certificates in Applied Mathematics and Neuroscience. His research emphasizes improving the generalizability of ML models through reasoning over knowledge and symbolic representations. He has developed algorithms for abductive theory formation, generative probabilistic models of grammar for semantic parsing, and frameworks for neuro-symbolic integration. Techniques used include Bayesian nonparametrics, approximate posterior inference, and combinatorial optimization. Active on GitHub , he maintains repositories like learning_to_search (transformer scaling analysis), prontoqa (synthetic QA dataset for LLM reasoning), and PWL (probabilistic abduction for theory induction). No formal awards or student advisees are listed in available texts.

Ankur ParikhView profile

Adjunct Assistant Professor

• Natural Language Processing
• Machine Learning
• Spectral Learning
• +3 more

Ankur Parikh is a staff research scientist at Google NYC and an adjunct assistant professor at New York University. His research focuses on natural language processing, machine learning, and spectral learning methods with applications to graphical models and biological networks. He holds a PhD from Carnegie Mellon University’s Machine Learning Department (2014), advised by Eric Xing, and an undergraduate degree in Computer Science and Applied Math from Princeton University. His work bridges theoretical advancements in machine learning with practical applications, including decomposable attention models for NLP, kernel graphical models, and network analysis of biological systems. Notable contributions include the TREEGL algorithm for gene network inference and spectral methods for latent structure discovery. He has been recognized with best paper awards at EMNLP and ISMB conferences. Education: PhD, Machine Learning, Carnegie Mellon University (2014) BS, Computer Science & Applied Math, Princeton University Parikh has taught advanced courses on spectral learning and probabilistic graphical models, including guest lectures at CMU and tutorials at Microsoft Research. His research is supported by an NSF Graduate Fellowship and has led to open-source implementations like the PLRE language modeling toolkit. Current affiliations include NYU’s machine learning community and Google’s NYC research team, with ongoing collaborations in NLP, computational biology, and statistical network analysis.

Michael CelentanoView profile

Research Fellow

• High-Dimensional Data Analysis
• Statistical Inference
• Machine Learning
• +4 more

Michael Celentano is a Research Fellow (Postdoctoral Miller Fellow) at the University of California, Berkeley's Department of Statistics, and a Member of Technical Staff at OpenAI. He holds a PhD in Statistics from Stanford University (2021), advised by Andrea Montanari, alongside master's (2016) and bachelor's (2014) degrees in Mathematics/Physics and Electrical Engineering from Stanford. His research focuses on high-dimensional data algorithms, bias correction in complex models, and first-order methods' statistical analysis. He collaborates with leading researchers like Yun Song and Martin Wainwright, and his work bridges semiparametric theory, causal inference, and biological applications. Celentano has organized the Online Causal Inference Seminar and contributed to the Simons Institute's Computational Complexity of Statistical Inference program. His honors include the Theodore W. Anderson Theory of Statistics Award and an NSF Graduate Research Fellowship. Research Interests: Algorithmic bias mitigation in high-dimensional prediction Average-case analysis of non-convex optimization Variational Bayesian inference High-dimensional causal inference Phylodynamic modeling in evolutionary biology Labs/Teams: Collaborates with the labs of Yun Song (UC Berkeley) and Martin Wainwright, contributing to interdisciplinary projects at the Simons Institute and OpenAI.

• Machine Learning
• Reinforcement Learning
• Neural Networks
• +3 more

Ruosong Wang is an Assistant Professor at Peking University , focusing on Reinforcement Learning , Neural Networks , and Optimization . His research bridges theoretical analysis with practical implementations in AI, particularly in deep learning and reinforcement learning frameworks. Research Interests : Wang’s work explores the intersection of Machine Learning Theory , Function Approximation , Generalization , and Algorithm Design . He investigates how overparameterized neural networks and infinitely wide deep nets can be optimized for small-data tasks, while addressing challenges in offline RL , preference-based learning , and graph neural networks . Article Trends : His publications (2019–2021) emphasize provably efficient algorithms for reinforcement learning, fine-grained theoretical analysis of neural network optimization, and hybrid models combining graph kernels with neural architectures. Key themes include sample efficiency , representation learning , and bounded eluder dimension in RL. Collaborations and Access : Wang collaborates with leading researchers at institutions like Carnegie Mellon University and UC Berkeley. All his articles are publicly accessible through arXiv or conference proceedings, with citations reflecting significant influence in machine learning and AI communities.

Yandi ShenView profile

Assistant Professor

• Nonparametric Statistics
• Semiparametric Statistics
• High-Dimensional Inference
• +6 more

Yandi Shen is an Assistant Professor in the Department of Statistics and Data Science at Carnegie Mellon University (CMU), part of the Dietrich College of Humanities and Social Sciences. He holds a Ph.D. in Statistics from the University of Washington (2021), advised by Fang Han and Daniela Witten. Prior to joining CMU, he was a Kruskal Instructor in Statistics at the University of Chicago (2021–2023) and a postdoctoral researcher at Yale University under Zhou Fan. His research focuses on nonparametric and semiparametric statistics, high-dimensional inference, applied probability, and optimization algorithms. Education: Ph.D. in Statistics (University of Washington, 2021); Postdoctoral work at University of Chicago and Yale University. Research Interests: Nonparametric and semiparametric methods High-dimensional statistical inference Applied probability and stochastic processes Empirical Bayes methods Optimization and algorithm design Statistical machine learning Teaching Experience: University of Washington: Teaching Assistant for advanced inference courses (STAT 581-583), probability (STAT 394-395), and applied statistics (STAT 528). University of Chicago: Instructor for courses like STAT 22400 (Applied Regression Analysis) and STAT 33611 (Gaussian Processes). Recent Research Trends: His publications emphasize theoretical advancements in high-dimensional statistics, including empirical Bayes estimation, gradient flows, and optimization in overparameterized models. Key areas include analyzing phase transitions in spline regression, universality in regularized estimators, and nonparametric mixture models under optimal transport distances. Labs/Teams: While no specific lab is named, his collaborative work spans statistical theory and applications, often involving interdisciplinary teams in data science and machine learning.

R. RaviView profile

Professor

• Operations Research
• Computer Science
• Combinatorial Optimization
• +4 more

R. Ravi is the Vasantrao Dempo Professor of Operations Research and Computer Science at Carnegie Mellon University's Tepper School of Business. He holds a B.Tech from IIT Madras and a Ph.D. from Brown University. His research focuses on combinatorial optimization, network design, and their applications in business and technology, particularly in supply chains, logistics, and online advertising. Ravi has held prestigious roles including Associate Dean for Intellectual Strategy, Chair of the Future Educational Delivery Committee, and Director of Analytics Strategy. He is an INFORMS Fellow (2017) and recipient of the 30-year Test of Time Award (2023) for his 1989 STOC paper. His work is supported by NSF, ONR, and industry grants. Ravi has advised over 25 Ph.D. students and contributed to numerous editorial and conference leadership roles. Education: Bachelor's: Computer Science, IIT Madras (1989) Master's and Ph.D.: Computer Science, Brown University (1991, 1993) Postdoctoral Fellowships: Princeton University and UC Davis (1993-1995) Research Interests: Optimization models for business-technology intersections, including supply chains, logistics, and online advertising. His methods blend theory with practical applications, leveraging funding from NSF, Google, and others. Awards & Honors: INFORMS Fellow (2017) NSF Career Award ACM STOC 30-Year Test of Time Award (2023) Current Roles: Director of Analytics Strategy at Tepper School, Amazon Scholar (since 2021), and adjunct faculty at CMU's Computer Science Department.

Christopher GenoveseView profile

Professor

• High-Dimensional Statistics
• Nonparametric Inference
• Computational Neuroscience
• +7 more

Christopher Genovese serves as Professor and Department Head of the Department of Statistics within Carnegie Mellon University's Dietrich College of Humanities and Social Sciences. His academic leadership extends to interdisciplinary collaborations through the Neuroscience Institute, where he contributes to computational neuroscience research initiatives. Dr. Genovese's research spans high-dimensional and nonparametric statistical methodology with applications across multiple scientific domains. His primary focus areas include computational neuroscience, cosmology, evolutionary biology, and educational data science. Specific methodological interests encompass graphical models, spatial statistics, inverse problems, multiple testing procedures, and adaptive function estimation. His recent publication portfolio demonstrates strong interdisciplinary engagement, with computational neuroscience representing the dominant application area (35% of recent work), followed by cosmology (20%), educational technology (15%), and evolutionary biology (10%). Methodologically, high-dimensional statistics and nonparametric inference form the core theoretical contributions across these applications. Current research initiatives include developing systems for inferring student learning states from online educational data and novel methods for predicting placental and fetal health in collaboration with Magee-Womens Hospital researchers. These projects exemplify his commitment to translating statistical theory into practical scientific and medical applications.

Alan FriezeView profile

Professor

• Combinatorics
• Computer Science
• Random Graphs
• +6 more

Alan Frieze is a University Professor at Carnegie Mellon University , affiliated with the Department of Mathematical Sciences. His research spans combinatorics, random graphs, algorithms, and probabilistic methods. Academic Rank: Professor Department: Mathematical Sciences Emails: frieze@cmu.edu, af1p@andrew.cmu.edu, alan@random.math.cmu.edu Research Interests: Frieze's work focuses on combinatorics, random graph theory, algorithm design, and probabilistic models. His recent publications address Hamiltonian cycles, rainbow subgraphs, and stochastic processes in graph theory. Scientific Awards: He has received prestigious honors including the Fulkerson Prize (1991), Guggenheim Fellowship (1997), and fellowships from the AMS and SIAM. Teaching Activities: Frieze has taught courses such as Random Graphs, Combinatorics, and Doctoral Thesis Research at Carnegie Mellon University.