Find Academic Supervisors

Amitabha BagchiView profile

Professor

• Data Algorithmics
• Probability and Networks
• Theoretical Computer Science
• +7 more

Amitabha Bagchi is a Professor in the Department of Computer Science and Engineering at IIT Delhi. His research spans data algorithmics, probability, networks, and theoretical computer science, with applications in distributed systems, social networks, and AI-driven platforms. He has published extensively in leading venues such as SIGMOD, VLDB, ICDE, AAAI, and KDD, often collaborating with students and researchers on problems involving graph algorithms, fairness, and large-scale data analysis. Research Interests: His primary research interests include Data Algorithmics, Probability and Networks, Theoretical Computer Science, Distributed Algorithms, Graph Algorithms, and Machine Learning Theory. He investigates algorithmic foundations for real-world problems such as food delivery optimization, social network analysis, and efficient data structures for streaming and large graphs. Publication Trends: Recent publications focus on fairness in gig economy platforms, efficient solvers for graph Laplacians, generalization in neural networks, and temporal graph querying. His work combines theoretical rigor with practical impact, often involving GPU acceleration, distributed computing, and data-aware algorithm design. Scientific Service: Editor, Algorithms (2020–present) Editor, Journal of Discrete Algorithms , Elsevier (2006–2018) Guest Editor, special issue on Algorithms for Shortest Paths in Dynamic and Evolving Networks , Algorithms (2021) Volume Editor for proceedings of ESA, ATMOS, COCOON, and others Conference Leadership: He has served on numerous program committees and as chair for conferences including ESA (Engineering Track, 2016), ATMOS (2020), and ICALP (2019). His involvement spans algorithmic engineering, transportation optimization, and theoretical computer science forums. Teaching: He currently teaches COL863: Special Topics in Theoretical Computer Science on concentration inequalities and their applications. He has previously taught advanced courses in algorithms and data structures.

Michael A OsborneView profile

Professor

• Machine Learning
• Bayesian Optimization
• Gaussian Processes
• +3 more

Michael A Osborne is Professor of Machine Learning at the University of Oxford and leads the Bayesian Exploration Lab . He serves as Director of the EPSRC Centre for Doctoral Training in Autonomous Intelligent Machines and Systems and co-directs the Oxford Martin AI Governance Initiative. His research focuses on Bayesian optimization, Gaussian processes, and probabilistic numerics with applications in quantum devices, battery modeling, and AI governance. Key Positions: Professor of Machine Learning, University of Oxford Official Fellow, Exeter College Co-founder of Mind Foundry Lead Researcher, Oxford Martin Programme on Technology and Employment Research Themes: Probabilistic modeling for quantum systems Uncertainty quantification in energy storage AI safety and societal impact analysis Automated experimental design Quantum device calibration Probabilistic numerical methods Technical Contributions: Bridging reality gap in quantum devices Efficient Bayesian quadrature techniques Personalized neurostimulation algorithms Automated measurement protocols Quantum-classical hybrid ML

Dai ZhongxiangView profile

Assistant Professor

• Large Language Models Inference
• Prompt Optimization
• In-context Learning
• +5 more

Dai Zhongxiang is an Assistant Professor and Presidential Young Fellow at the School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHKSZ), where he joined in August 2024. Previously, he was a Postdoctoral Associate at MIT's Laboratory for Information and Decision Systems (January-June 2024) and a Postdoctoral Fellow at the National University of Singapore's Department of Computer Science (April 2021-December 2023). He completed his Ph.D. in Artificial Intelligence at NUS under the supervision of Bryan Kian Hsiang Low and Patrick Jaillet. Dr. Dai's research focuses on the intersection of theoretical and practical AI, with particular emphasis on large language models (LLMs) and optimization techniques. His work spans both theoretical foundations of multi-armed bandits and Bayesian optimization, as well as practical applications in LLM inference, including prompt optimization, in-context learning, personalization of LLMs, LLM-based agents, and scaling up test-time computation of LLMs. His research approach often bridges theoretical principles with real-world applications, particularly in AI4Science problems. His recent publications demonstrate a clear trend toward advancing LLM capabilities through optimization techniques, with increasing focus on practical deployment challenges. The research spans both theoretical contributions to optimization theory and applied work on enhancing LLM performance in real-world scenarios. His work on dueling bandits, neural bandits, and zeroth-order optimization has been consistently published in top-tier venues including NeurIPS, ICML, ICLR, and ACL. Presidential Young Fellow, CUHKSZ (2024) Dean's Graduate Research Excellence Award, NUS (2021) Research Achievement Award × 2, NUS (2019 & 2020) Singapore-MIT Alliance Graduate Fellowship (2017) Dr. Dai actively mentors multiple Ph.D. students and research assistants, with several of his students' papers accepted to top conferences. His research has received significant attention, with invitations to serve as Area Chair for NeurIPS 2025 and ICLR 2025, reflecting his growing influence in the machine learning community. His work bridges theoretical machine learning with practical applications in large-scale AI systems.

Jelani NelsonView profile

Professor

• Theoretical Computer Science
• Algorithms
• Data Streams
• +8 more

Jelani Nelson is a Professor and Department Chair in the UC Berkeley EECS Department (College of Engineering). His work focuses on theoretical computer science , particularly algorithms , data streams , dimensionality reduction , and privacy-preserving computation . Advising : Current students include Ishaq Aden-Ali, Xin Lyu, Mihir Singhal, and Hongxun Wu (co-advised with leading researchers). Education : PhD from MIT (George M. Sprowls Award), M.Eng from MIT. Research Highlights : Developed foundational results in Johnson-Lindenstrauss dimensionality reduction (optimality, sparse embeddings). Advancements in differential privacy (lower bounds, private mean estimation, threshold learning). Pioneering work on streaming algorithms for heavy hitters, norm estimation, and graph problems. Innovations in compressed sensing and oblivious subspace embeddings . Scientific Awards : PODS Best Paper Award (2011, 2022) IBM Pat Goldberg Memorial Best Paper Award (2011) George M. Sprowls Award for MIT doctoral thesis (2009) NeurIPS 2020 Spotlight Presentation

Ben FischView profile

Assistant Professor

• Cryptography
• Distributed Systems
• Blockchain Technology
• +5 more

Ben Fisch is an Assistant Professor of Computer Science at Yale University's School of Engineering & Applied Science. He is also the co-founder of Espresso Systems, a company focused on blockchain infrastructure. His research focuses on privacy and verifiability in decentralized systems like Bitcoin and Ethereum, with applications in digital finance and healthcare. Dr. Fisch received his B.A. from the University of Pennsylvania and completed his Ph.D. at Stanford University, where he worked with Dan Boneh in the applied cryptography research group. His educational background provided the foundation for his work at the intersection of cryptography, distributed systems, and economics. His research centers on leveraging cryptographic tools such as succinct non-interactive zero-knowledge proofs (zk-SNARKs), private information retrieval, and homomorphic encryption to address challenges in verifiable computation, verifiable storage, and verifiable fairness. He has made significant contributions to verifiable delay functions (VDFs) and proofs of replication, which have been adopted by major blockchain projects including Ethereum 2.0, Chia, and Filecoin. His work on Filecoin's Proofs of Replication has helped the network reach over 1.5 exabytes of storage capacity. His publication record shows a clear trend toward increasingly sophisticated cryptographic protocols for blockchain applications, with recent work focusing on data availability for Bitcoin rollups, efficient folding schemes for pairing-based arguments, and privacy pools with proof-carrying disclosures. His research bridges theoretical cryptography with practical implementations that have real-world impact in decentralized systems. His notable recognition includes: Best Paper Finalist at ACM CCS 2017 for 'Iron: Functional Encryption using Intel SGX' Dr. Fisch's research has led to significant technology transfer, most notably with his work on Verifiable Delay Functions (VDFs) sparking a multimillion dollar industry initiative through the VDF Alliance. His research on Proofs of Replication forms the basis of Filecoin's incentive layer and consensus protocol. His newer SNARK system Basefold is being used by several commercial products. He maintains active collaborations across academia and industry, with publications spanning top conferences in cryptography and security. As co-founder of Espresso Systems, Dr. Fisch leads a team developing next-generation blockchain infrastructure, particularly focusing on sequencing layers for rollups. His work bridges academic research with practical implementation, ensuring that theoretical advances in cryptography find real-world applications in decentralized systems.

Daniel A. SpielmanView profile

Professor

• Spectral Graph Theory
• Algebraic Graph Theory
• Laplacian Matrices
• +7 more

Daniel A. Spielman is a Sterling Professor of Computer Science, Statistics & Data Science, and Mathematics at Yale University. He serves as the inaugural James A. Attwood Director of the Institute for Foundations of Data Science (FDS) and was previously co-Director of the Yale Institute for Network Science (YINS). He is also a member of TILOS, the NSF Institute for Learning-Enabled Optimization at Scale. His research interests span Spectral Graph Theory, Algebraic Graph Theory, Laplacian Matrices, Expander Graphs, and Random Walks on Graphs. Spielman has made fundamental contributions to understanding the mathematical foundations of data science, including work on smoothed analysis of algorithms, spectral sparsification, and solutions to the Kadison-Singer problem. Spielman's publications demonstrate a consistent focus on developing efficient algorithms with strong theoretical foundations. His work bridges pure mathematics, theoretical computer science, and practical applications in network analysis and machine learning. His research has evolved from foundational work on smoothed analysis to recent contributions in experimental design using discrepancy theory. His scientific honors include: Nevanlinna Prize for contributions to mathematical aspects of computer science Two Gödel Prizes (2008 and 2015) for outstanding papers in theoretical computer science MacArthur Fellowship ('Genius Grant') Simons Investigator award Membership in the National Academy of Sciences and American Academy of Arts and Sciences Spielman has advised numerous PhD students who have gone on to prominent positions in academia and industry. His teaching includes advanced courses in Spectral Graph Theory and Computation and Optimization. He has developed important software packages like Laplacians.jl for solving Laplacian linear equations and related problems.

Florian SchäferView profile

Assistant Professor

• Numerical Analysis
• Computational Mathematics
• Machine Learning
• +9 more

Florian Schäfer is an Assistant Professor at the School of Computational Science and Engineering at Georgia Tech. His research spans numerical computation, statistical inference, and competitive games, with applications in materials science, turbulence modeling, computer graphics, and computational geometry. He will join the Courant Institute at NYU in September 2025. PhD in Applied and Computational Mathematics, Caltech Bachelor’s and Master’s in Mathematics, University of Bonn His work focuses on information geometric mechanics to design structure-preserving numerical methods for continuum mechanics. This includes: State-of-the-art solvers for elliptic PDEs via Gaussian elimination and conditional independence Efficient multi-agent optimization algorithms Information geometric regularization for compressible fluid dynamics Enabling the first compressible fluid simulation exceeding 100 trillion grid cells His recent research trends integrate: Machine learning for materials science (e.g., active learning, Bayesian approaches) Stochastic modeling of microstructures and phase-field problems Neural operators for super-resolution fluid dynamics Generative models for polycrystalline material datasets Optimal transport and diffusion models for conditional density transformations High-performance computing at extreme scales Florian collaborates with researchers including Houman Owhadi, Jessie Liu, Spencer Bryngelson, Tamer Zaki, and Ali Mani. He actively presents at conferences like SIAM and UCLA seminars, and is recruiting PhD students for work at the Courant Institute starting 2025.

• Scientific Machine Learning
• Numerical Linear Algebra
• Numerical Multilinear Algebra
• +7 more

Peter Benner is a Professor and Director at the Max Planck Institute for Dynamics of Complex Technical Systems in Magdeburg, where he leads the Computational Methods in Systems and Control Theory group. He also holds an Honorarprofessor position for Mathematics at Otto-von-Guericke Universität Magdeburg since 2011. Benner has previously served as Managing Director of the Max Planck Institute during multiple periods (2013-2014, 2021-2022, and 2025-2026), demonstrating his leadership in the field. Benner's research focuses on Scientific Machine Learning, Numerical Linear and Multilinear Algebra, Model Order Reduction and Reduced-order Modeling, Numerical Methods in Systems and Control Theory, PDE Constrained Optimization, High-performance and Power-aware Computing, and Mathematical Software development. His work bridges theoretical mathematics with practical engineering applications, particularly addressing challenges in large-scale dynamical systems. Analysis of his recent publications reveals a strong emphasis on developing efficient computational methods for complex systems. Benner has pioneered approaches combining model order reduction with tensor methods to tackle high-dimensional problems in uncertainty quantification and PDE-constrained optimization. His work shows a consistent trend toward integrating data-driven techniques with traditional model-based approaches, particularly for nonlinear and parametric systems. Throughout his career, Benner has actively mentored students and collaborated with researchers worldwide, delivering numerous invited talks at prestigious institutions and conferences across Europe, North America, and Asia. His research has received significant funding, supporting the development of mathematical software and computational methods for industrial applications. Benner leads the Computational Methods in Systems and Control Theory department at the Max Planck Institute, which focuses on developing and implementing advanced numerical methods for large-scale dynamical systems. The group maintains strong connections with both theoretical mathematics and practical engineering applications, particularly in fluid dynamics, energy systems, and control theory.

• Theoretical Computer Science
• Graph Algorithms
• Dynamic Algorithms
• +7 more

Nicole Wein is an Assistant Professor in the Computer Science and Engineering Division of the Department of Electrical Engineering and Computer Science (EECS) at the University of Michigan, College of Engineering. Her research lies in theoretical computer science, focusing on graph algorithms, dynamic algorithms, parameterized algorithms, distributed algorithms, online algorithms, and fine-grained complexity. She is part of the Theory of Computation Lab and advises both PhD and undergraduate researchers. PhD, Massachusetts Institute of Technology (MIT), advised by Virginia Vassilevska Williams Postdoctoral Fellow, DIMACS Research Fellow, Simons Institute, UC Berkeley MS, Stanford University BS, Computer Science/Math, Harvey Mudd College Her research explores fundamental algorithmic questions in combinatorial settings, particularly how algorithms handle dynamic data, extract information efficiently (e.g., in linear time), and understand shortest path structures in graphs—especially directed ones. She investigates problems in distance estimation, spanners, hopsets, dynamic graph algorithms, and hardness of approximation. Her work combines theoretical depth with practical implications for algorithm design. The recent publications reflect a strong trend in fine-grained complexity and graph algorithm design, with a focus on proving tight bounds, developing efficient approximations, and understanding structural limitations in directed and dynamic graphs. Her work frequently appears in top venues such as STOC, FOCS, SODA, and ICALP, often in collaboration with leading researchers in the field. Scientific Awards and Recognition: Invited to special issue of SIAM Journal on Computing (SICOMP) (FOCS 2022 paper) Invited to Highlights of Algorithms (HALG) (FOCS 2022 paper) Invited to minisymposium at CANADAM (ESA 2022 paper) Work featured in Quanta Magazine Nicole Wein actively mentors students, including current PhD student Jubayer Nirjhor and former undergraduate researchers like Sam Hiken (now pre-doc at MIT). She has served on program committees for major conferences including SODA, FOCS, ICALP, and ITCS, and co-organized the DIMACS workshop on Modern Techniques in Graph Algorithms (2023). She also contributes to the academic community through outreach, such as her article offering reassurance to early-stage PhD students in theoretical computer science. She leads and participates in collaborative research groups and workshops, emphasizing supercollaboration and interdisciplinary communication in algorithms. Her lab fosters a strong research environment in theoretical computer science at the University of Michigan.

• Information Theory
• Cryptography
• Lattice Theory
• +5 more

Cong Ling is a Professor of Information Theory and Cryptography at Imperial College London's Department of Electrical and Electronic Engineering, within the Faculty of Engineering. His research focuses on lattice theory and its applications in coding, cryptography, quantum information, and number theory. Key affiliations include the Academic Centre of Excellence in Cyber Security Research and the Engineering Secure Software Systems group. Education details are not explicitly provided in the text, but his professional experience indicates advanced qualifications in electrical engineering and mathematics. Research interests span lattice-based cryptography, post-quantum security, algebraic coding theory, and quantum-resistant algorithms. His work bridges information theory and number theory, with contributions to MIMO systems, secure communication protocols, and cryptographic protocol design. Recent publications emphasize lattice reduction techniques, quantum algorithms for the shortest vector problem, and advancements in polar codes. Notable trends include exploration of non-commutative algebras for cryptography, Gaussian sampling optimizations, and hybrid quantum-classical approaches to hard integer problems. Over 50+ articles published since 2018 reflect his leadership in lattice-based research and quantum-safe technologies. Awards: None explicitly listed in the text. Grants/Advising: No specific grants or student advisees mentioned; focus remains on collaborative research outputs. Labs/Teams: Associated with Imperial's Cyber Security Research groups and quantum engineering initiatives.

Ivan DokmanicView profile

Assistant Professor

• Machine Learning
• Signal Processing
• Inverse Problems
• +11 more

Ivan Dokmanic is an Assistant Professor at the Coordinated Science Laboratory (CSL) within the University of Illinois . His research bridges signal processing , machine learning , and applied inverse problems , with a focus on acoustics, biomedical imaging, and distance geometry. Current Role : Assistant Professor, CSL Email : dokmanic@illinois.edu Research Interests : Dokmanic explores machine learning applications in inverse problems , particularly distance geometry for molecular imaging and acoustics . His work includes unlabeled sensing , where distances between points are known but their arrangement is not. This has implications for powder diffraction , indoor localization , and echo modeling . Article Trends : His recent publications emphasize distance geometry in machine learning , acoustic signal processing , and inverse problem theory . Key areas include molecular imaging , audio encryption , and sensor positioning . Collaborative work spans medical imaging , cyberphysical systems , and geometric invariants . 2016 Google Faculty Award NSF Grant (1 year, $157,079) Students and Grants : Dokmanic mentors PhD students like Puoya, Shuai, and Anadi. His research is funded by the National Science Foundation , Google , VISA , and nVidia .

• Machine Learning
• Computer Vision
• Robotics
• +7 more

Raquel Urtasun is a Full Professor in the Department of Computer Science at the University of Toronto and a co-founder of the Vector Institute for AI. She is also the Founder and CEO of Waabi, an autonomous vehicle company. Previously, she was Chief Scientist and Head of R&D at Uber ATG (2017–2021) and held faculty positions at the Toyota Technological Institute at Chicago (TTIC) and as a visiting professor at ETH Zurich. Her research spans machine learning, computer vision, robotics, and AI with a strong focus on autonomous driving and 3D perception. Education: Bachelor's degree, Universidad Pública de Navarra, 2000 Ph.D., Computer Science, École Polytechnique Fédérale de Lausanne (EPFL), 2006 Postdoctoral studies, MIT and UC Berkeley Raquel Urtasun's research focuses on developing AI systems for self-driving cars, emphasizing efficient perception using minimal sensors. Her work includes 3D scene understanding, stereo vision, optical flow, semantic segmentation, and object detection. She has developed the KITTI benchmark suite, widely used in autonomous driving research. Her lab is an NVIDIA NVAIL lab, reflecting its leadership in AI innovation. Her recent publications show a consistent trend in deep learning for visual perception, particularly in stereo matching, optical flow, 3D object detection, and semantic segmentation. These works integrate deep neural networks with structured models like CRFs and MRFs, pushing the boundaries of accuracy and efficiency in scene understanding for autonomous systems. Scientific Awards: NSERC E.W.R. Steacie Fellowship NVIDIA Pioneers of AI Award Google Faculty Research Awards (multiple) Amazon Faculty Research Award Connaught New Researcher Award Fallona Family Research Award Best Paper Runner Up at CVPR 2013 and 2017 UPNA Alumni Award Chatelaine 2018 Woman of the Year Adweek 2018 Toronto's Top Influencers Urtasun has advised numerous PhD and Master’s students, many of whom now hold faculty or research scientist positions at institutions like UIUC, NYU, UBC, MIT, and companies including Google, Amazon, NVIDIA, and Apple. She has secured significant research grants from NSERC, Google, Amazon, and NVIDIA. Her leadership extends to organizing workshops and serving as Area Chair and Program Chair at top conferences like CVPR, ICML, and NeurIPS. Labs and Teams: She leads a research group at the University of Toronto focused on AI for autonomous systems. Her team has been recognized as an NVIDIA NVAIL lab, and she continues to mentor students and postdocs working on cutting-edge problems in robotics and machine learning, both at UofT and through her company Waabi.

Per Christian HansenView profile

Professor

• Numerical Analysis
• Numerical Linear Algebra
• Iterative Reconstruction Methods
• +8 more

Per Christian Hansen is a Professor at the Department of Applied Mathematics and Computer Science (DTU Compute), Technical University of Denmark (DTU), where he leads the Section for Scientific Computing. He is a VILLUM Investigator and heads the CUQI (Computational Uncertainty Quantification for Inverse Problems) research initiative, aiming to develop accessible computational platforms for uncertainty quantification in inverse problems. His expertise lies in numerical analysis, numerical linear algebra, iterative reconstruction methods, and computational inverse problems, with applications in tomography, signal analysis, and plasma physics. His research integrates theoretical analysis—such as perturbation and convergence analysis—with the development of robust, adaptive, and efficient computational methods. He has co-authored five books, over 100 scientific papers, and several widely used MATLAB software packages, including IR Tools and Regularization Tools. His recent work (2023–2025) emphasizes uncertainty quantification, Bayesian inversion, and high-dimensional tomography in fusion plasmas, reflecting a strong trend toward probabilistic and robust modeling in inverse problems. He is a SIAM Fellow (2015) for his contributions to computational methods for rank-deficient and discrete ill-posed problems and regularization techniques. His scientific leadership is evident in both theoretical advances and practical software implementations. He actively collaborates across disciplines, particularly in nuclear fusion and medical imaging, and continues to supervise PhD students and publish in top-tier journals such as Inverse Problems , SIAM Journal on Scientific Computing , and Nuclear Fusion . SIAM Fellow (2015) VILLUM Investigator He advises PhD and Master’s students in computational mathematics and inverse problems, and his research is supported by major grants, including the VILLUM Investigator award. He leads the CUQI team, which develops open-source tools for non-experts to apply uncertainty quantification in inverse problems. His lab focuses on creating modeling frameworks that bridge theory, computation, and real-world applications in materials science, imaging, and plasma diagnostics.

Bryon AragamView profile

Associate Professor

• Causality
• Statistical Machine Learning
• Probabilistic Modeling
• +6 more

Bryon Aragam is an Associate Professor of Econometrics and Statistics and Robert H. Topel Faculty Scholar at the University of Chicago Booth School of Business. His research focuses on the intersection of causality, statistical machine learning, and probabilistic modeling, with particular emphasis on applications to artificial intelligence systems including large language models like ChatGPT and generative models like DALL-E. Dr. Aragam completed his PhD in Statistics and a Masters in Applied Mathematics at UCLA, where he was an NSF graduate research fellow. Prior to joining the University of Chicago, he was a project scientist and postdoctoral researcher in the Machine Learning Department at Carnegie Mellon University. Research Focus: Causal structure learning in probabilistic generative models Key Areas: Causal machine learning, deep generative models, latent variable models, statistical learning theory Applications: AI interpretability, ethics, and fairness in artificial intelligence systems Teaching: Business Statistics, Econometrics and Statistics Colloquium His recent publications demonstrate a strong theoretical foundation combined with practical applications, particularly in understanding and improving AI systems. His work spans causal discovery, graphical models, deep learning, and latent variable modeling, with particular attention to the theoretical properties of these methods and their applications to real-world AI challenges. The research shows a progression toward increasingly complex problems in causal representation learning and AI interpretability. Scientific Awards: Robert H. Topel Faculty Scholar NSF Graduate Research Fellow Dr. Aragam's work has been published in top statistics and machine learning venues including the Annals of Statistics, Neural Information Processing Systems (NeurIPS), the International Conference on Machine Learning (ICML), and the Journal of Machine Learning Research (JMLR). His research group publishes broadly across both statistical and machine learning communities, demonstrating the interdisciplinary nature of his work at the intersection of statistics, machine learning, and causal inference. As a data science consultant for technology and marketing firms, Dr. Aragam has applied his expertise to problems in survey design, customer retention, logistics, and ranking, bridging the gap between theoretical research and practical applications.

Aaron RothView profile

Professor

• Algorithms
• Machine Learning
• Differential Privacy
• +10 more

Aaron Roth is the Henry Salvatori Professor of Computer and Cognitive Science at the University of Pennsylvania, affiliated with the Department of Computer and Information Science in the School of Engineering and Applied Science. He holds a secondary appointment in the Department of Statistics and Data Science at the Wharton School and is associated with several research centers including PRiML, the Warren Center for Network and Data Sciences, and the AMCS program. He received his PhD from Carnegie Mellon University under Avrim Blum and was a postdoc at Microsoft Research New England. His research focuses on algorithms and machine learning, particularly in private data analysis, fairness in machine learning, game theory, mechanism design, and learning theory. His work bridges theoretical computer science with societal concerns, advocating for ethically aware algorithm design. He co-authored the book The Ethical Algorithm with Michael Kearns, which explores how to embed social values like privacy and fairness into algorithmic systems. His recent publications show a strong trend toward uncertainty quantification, multicalibration, conformal prediction, and fairness in reinforcement learning and high-dimensional settings. He frequently publishes in top-tier venues such as STOC, FOCS, ICML, NeurIPS, and COLT, often with a focus on rigorous theoretical foundations with practical implications. Hans Sigrist Prize Presidential Early Career Award for Scientists and Engineers (PECASE) Alfred P. Sloan Research Fellowship NSF CAREER award Google Faculty Research Award Amazon Research Award Yahoo Academic Career Enhancement award Roth has advised numerous PhD students and postdocs, many of whom now hold academic or industry research positions. He is also an Amazon Scholar at AWS and has served in advisory roles for companies like Apple, Facebook, Leapyear, and Spectrum Labs. He has been active in organizing workshops and tutorials on differential privacy, fairness, and adaptive data analysis, and has given keynotes at major conferences and institutions worldwide. He leads research groups and collaborates widely across Penn, focusing on responsible AI, privacy, and algorithmic fairness. His lab produces foundational work on calibration, unlearning, privacy-preserving learning, and equitable decision-making systems.