Keegan Kang

Keegan Kang joined Bucknell University in 2022. Prior to this appointment, he spent five years as a faculty fellow/lecturer at the Singapore University of Technology and Design.

Pronouns
He, him, his, himself

Educational Background

• Cornell University, Ph.D. in Statistics
• Cornell University, M.S. in Statistics
• Warwick University, B.Sc. MMORSE (Mathematics and Statistical Concentration)

Research Interests

• Computational Statistics
• Random Projections
• Locality Sensitive Hashing schemes
• Machine Learning
• Educational Pedagogy

Selected Publications

Underlined names denote Bucknell undergraduate students

Keegan Kang, Avery Hood '27, and Benedict H.W. Wong. (2026) Understanding Circulant Permutation to Extend the CMinHash Estimator. To appear in the Proceedings of the Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS).
(https://datascience.scholar.bucknell.edu/2026/10/08/bucknell-research-revisiting-minhash-leads-to-new-methods-and-simpler-proofs/)

Noah Thomas '28, Eric Yang '29, Benedict H.W. Wong, and Keegan Kang. (2026) A Second Look at Broder's MinHash Without Alignment. To appear in the Journal of Computer Science and Technology.

Amit Sharma, Mohammad Azhar Khan, Rameshwar Pratap, and Keegan Kang. (2026) Improving TensorSketch Using Complex Random Variables. In the Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence (UAI).

Rameshwar Pratap, Bhisham Dev Verma, and Keegan Kang. (2026) Stochastic Trace and Diagonal Estimation for Tensors. In Theoretical Computer Science, 2026.

Keegan Kang, Kerong Wang '24, Ding Zhang '23, Rameshwar Pratap, Bhisham Dev Verma, and Benedict H.W. Wong. (2026) It's All In The Exponential Family: An Equivalence Between Maximum Likelihood Estimation and Control Variates for Sketching Algorithms. In Proceedings of the 29th Annual Conference on Artificial Intelligence and Statistics (AISTATS).
(https://datascience.scholar.bucknell.edu/2026/05/05/bucknell-faculty-paper-accepted-at-aistats-2026/)

Dubey PP., Verma BD., Pratap R., and Kang K. (2022) Improving sign-random-projection via count sketch. 38th Conference on Uncertainty in Artificial Intelligence.
https://openreview.net/pdf?id=StLUq88jqx9

Kang, K., Wong WP., Liu XG., Kushnarev S., Tan DY., Ortiz O., Goyal, S., Singhal, R. (2021) A personalized online homework system in a freshman engineering linear algebra course. IEEE International Conference on Engineering, Technology Education (TALE).
(https://ieeexplore.ieee.org/document/9678890)

Kang K., Kushnarev, S., Wong, WP., Pratap, R., Yeo H., Chen YJ. (2021) Improving Hashing Algorithms for Similarity Search via MLE and the control variates trick. 13th Asian Conference on Machine Learning.
(https://proceedings.mlr.press/v157/kang21a.html)

Kang, K. (2021) Correlations between random projections and the bivariate normal. Data Mining and Knowledge Discovery.
(https://link.springer.com/article/10.1007/s10618-021-00764-6)

Kang, K., Kushnarev S., Wong WP., Ortiz O., and Shihang JC. (2020) Impact of virtual reality on the visualization of partial derivatives in a multivariable calculus class. IEEE Access, 8:58940–58947, 2020.
(https://ieeexplore.ieee.org/document/9045957)

Kang, K. and Wong, WP. (2018), Improving Sign Random Projections With Additional Information. 35th International Conference on Machine Learning, 2018
(https://proceedings.mlr.press/v80/kang18b.html)