Sanjoy Dasgupta — LLMpedia

Sanjoy Dasgupta
Name	Sanjoy Dasgupta
Fields	Computer Science, Machine Learning, Cognitive Science
Workplaces	University of California, San Diego; University of California, San Diego Department of Computer Science and Engineering; University of California, San Diego Halıcıoğlu Data Science Institute
Alma mater	Massachusetts Institute of Technology; University of California, Berkeley
Doctoral advisor	John Lafferty; Stuart Russell
Known for	Machine learning theory, clustering, kernel methods, perceptual learning

Contents

Sanjoy Dasgupta is an Indian-American computer scientist and academic known for contributions to machine learning, artificial intelligence, and computational learning theory. He has held faculty positions at the University of California, San Diego and contributed to research linking algorithmic theory with perceptual and cognitive models developed in laboratories such as the MIT Media Lab and departments at UC Berkeley. His work spans algorithm design, statistical theory, and applications influencing researchers at institutions including Stanford University, Princeton University, Carnegie Mellon University, Harvard University, and Columbia University.

Early life and education

Dasgupta was educated in India before moving to the United States for graduate study, engaging with research communities at the Massachusetts Institute of Technology and the University of California, Berkeley. At UC Berkeley he studied topics related to statistical learning theory and interacted with scholars affiliated with the International Conference on Machine Learning and the Neural Information Processing Systems conference. During his doctoral training he worked alongside advisors involved in projects connected to the Association for Computing Machinery and the Institute of Electrical and Electronics Engineers.

Dasgupta has served on the faculty of the University of California, San Diego, contributing to the Department of Computer Science and Engineering and interdisciplinary initiatives such as the Halıcıoğlu Data Science Institute. He has taught courses that intersect curricula at the School of Engineering and collaborations with centers like the Salk Institute for Biological Studies and the San Diego Supercomputer Center. His academic service includes organizing workshops at venues such as the Conference on Learning Theory and participation in program committees for the International Conference on Machine Learning, the Neural Information Processing Systems conference, and the European Conference on Machine Learning. He has advised students who went on to positions at Google Research, Microsoft Research, DeepMind, OpenAI, and research groups at IBM Research.

Dasgupta's research includes foundational work on clustering algorithms related to theories developed in the KDD Conference and the SIGMOD Conference communities, and theoretical analyses that connect to advances in kernel methods explored at the International Conference on Artificial Intelligence and Statistics. He developed analyses of randomized algorithms that have been cited alongside studies from Larry Page, Sergey Brin, and researchers at Yahoo! Research and Bell Labs. His contributions include probabilistic bounds on nearest-neighbor methods that relate to classical results by Thomas Cover and Peter Hart, and extensions linking to spectral techniques investigated in the IEEE Symposium on Foundations of Computer Science and the ACM Symposium on Theory of Computing. Dasgupta's work on perceptual organization draws on themes from the Psychonomic Society, the Cognitive Science Society, and experimental paradigms used by labs at MIT, Harvard University, and the University of Pennsylvania. He has published results influencing applications in information retrieval practiced at Yahoo!, clustering approaches used in Facebook and Twitter analytics, and methods adapted by teams at Adobe Research and NVIDIA Research.

Dasgupta has received recognition from venues and organizations that include invited presentations at the International Conference on Machine Learning and fellowships associated with graduate support programs linked to NSF-funded initiatives and trusts with ties to the Fulbright Program and the Sloan Foundation. He has been invited to keynote or present at symposia sponsored by the Association for the Advancement of Artificial Intelligence and panels at the American Association for the Advancement of Science. His students and collaborators have been recipients of awards at conferences such as the Neural Information Processing Systems conference, the Conference on Neural Information Processing Systems, and the ACM Conference on Knowledge Discovery and Data Mining.

Dasgupta's publications appear in proceedings and journals associated with the International Conference on Machine Learning, Neural Information Processing Systems, Journal of Machine Learning Research, and the IEEE Transactions on Pattern Analysis and Machine Intelligence. Representative works include papers on clustering and learning theory cited alongside research from Kearns and Vazirani, and comparative studies referenced by authors at Microsoft Research and Google Research. His manuscripts have been discussed at workshops at Stanford University, Princeton University, Columbia University, and Cornell University.

Category:Computer scientists Category:Machine learning researchers Category:University of California, San Diego faculty