Daniel J. Hsu - Department of Computer Science and Data Science Institute, Columbia University

I work on algorithmic statistics and machine learning. My research is part of broader efforts in Foundations of Data Science, Machine Learning, and Theory of Computation at Columbia.

If you are a (current or prospective) student interested in coming to Columbia and/or working with me on research, or if you are generally interested in getting started in machine learning and/or research, please check this page of frequent answers to questions.

My papers can be found by following this link. (See also arXiv and Google Scholar.)

I am on sabbatical January-May 2023.
Slides for talk on “Algorithms for multi-group learning” at Harvard in December 2022.
Slides for talk on “Computational lower bounds for Tensor PCA” at ENSAE/École Polytechnique in November 2021.

People

I’m lucky to be able to work with several outstanding students and postdocs.

Students
- Navid Ardeshir (Ph.D. in progress)
- Jagdeep Bhatia (High school diploma, 2020; → MIT)
- Samuel Deng (M.S., 2021; Ph.D. in progress)
- Rishabh Dudeja (Ph.D., 2021; → Harvard)
- Arushi Gupta (B.S., 2016; M.S., 2018; → Princeton)
- Giannis Karamanolakis (Ph.D., 2022; → Amazon Alexa AI)
- Clayton Sanford (Ph.D. in progress)
- Kevin Shi (Ph.D., 2020; → Facebook)
- Geelon So (M.S., 2019; → UC San Diego)
- Kiran Vodrahalli (Ph.D., 2022; → Google Brain)
- Ji Xu (Ph.D., 2020; → Two Sigma)
- Keyang Xu (Ph.D. in progress)
- Mingyue Xu (M.S., 2022)
Postdocs
- Daniel G. Alabi
- Debmalya Mandal (→ Max Planck Institute for Software Systems)
- Christopher Tosh (→ Memorial Sloan-Kettering Cancer Center)

I’ve also worked with other fantastic students on their thesis research, including: Mathias Lécuyer, Avner May, Cun Mu, Karl Stratos, José Manuel Zorrilla Matilla.

Service

Associate editor / action editor
- ACM Transactions on Algorithms (2017-)
- Journal of Machine Learning Research (2022-)
- SIAM Journal on Mathematics of Data Science (2021-)
Program chair / senior program committee / area chair
- Conference on Learning Theory 2011, 2013, 2015, 2016, 2017, 2018, 2019 (co-chair with Alina Beygelzimer), 2020, 2021, 2022
- International Conference on Machine Learning 2012, 2013, 2015, 2016, 2017
- Conference on Neural Information Processing Systems 2012, 2013, 2017, 2019, 2021
- International Conference on Artificial Intelligence and Statistics 2016, 2017, 2019
- Conference on Algorithmic Learning Theory 2017, 2018, 2019, 2021, 2022, 2023
Workshop / seminar organization
- FOCS 2021 Workshop on Machine Learning (February 7-8, 2022)
- Columbia Year of Statistical Machine Learning (Fall 2019-Spring 2020)
- Columbia DSI/TRIPODS Deep Learning Workshop (March 15, 2019)
- Columbia Foundations of Data Science Seminar (Fall 2015)
- ICML 2014 Method of Moments and Spectral Learning (June 25, 2014)
- DIMACS/CCICADA Systems and Analytics of Big Data (March 17-18, 2014)
- NeurIPS 2013 Spectral Learning (December 10, 2013)
- ICML 2013 Spectral Learning (June 21, 2013)

Teaching

Thanks

I am grateful for support provided by the National Science Foundation, the National Aeronautics and Space Administration, the Alfred P. Sloan Foundation, the Columbia Data Science Institute, Bloomberg, Google, JP Morgan, NVIDIA, Two Sigma, and Yahoo.