Kan Xu
Department of Economics
University of Pennsylvania
The Ronald O. Perelman Center for Political Science and Economics
133 South 36th Street
Philadelphia, PA 19104
kanxu [AT] upenn [DOT] edu
Working Papers
Learning Across Bandits in High Dimension via Robust Statistics
(with Hamsa Bastani)
Major Revision, Management Science
3rd Place, IBM Service Science Best Student Paper Award (2022)
Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings
(with Xuanyi Zhao, Hamsa Bastani and Osbert Bastani)
Under Review, Management Science
- Preliminary version in ICML, 2021
Safely Bridging Offline and Online Reinforcement Learning
(with Wanqiao Xu, Hamsa Bastani and Osbert Bastani)
- Preliminary version in AISTATS, 2023
Robust Generalization of Quadratic Neural Networks via Function Identification
(with Hamsa Bastani and Osbert Bastani)
Two-Stage Maximum Score Estimator
(with Wayne Gao and Sheng Xu)
Publications
Safely Bridging Offline and Online Reinforcement Learning
(with Wanqiao Xu, Hamsa Bastani and Osbert Bastani)
International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings
(with Xuanyi Zhao, Hamsa Bastani and Osbert Bastani)
International Conference on Machine Learning (ICML), 2021
Software
R Package: EbayesThresh
(with Bernard W. Silverman, Ludger Evers, Peter Carbonetto and Matthew Stephens)