About me

I am a Ph.D. candidate in the Department of Statistics at the University of Washington. I am fortunate to be advised by Zaid Harchaoui and Soumik Pal. Prior to that, I received my B.S. in mathematics and applied mathematics at Tsinghua University.

I am broadly interested in safe and interpretable machine learning with applications in natural language processing. I am also excited about optimal transport and its applications in statistics and machine learning.

Contact me at liu16 [at] uw [dot] edu.


Upcoming presentations

  • 08/25/2022: Presentation at COMPSTAT 2022 on large-scale entropy regularized optimal transport independence criterion.
  • 08/08/2022: Presentation at JSM 2022 on independence testing with entropy regularized optimal transport.
  • 07/03/2022: Presentation at COLT 2022 on orthogonal statistical learning with self-concordant loss.
  • 06/27/2022: Presentation at PIMS-IFDS-NSF Summer School on Optimal Transport on entropy regularized optimal transport independence criterion.

News

  • 05/14/2022: Our paper on orthogonal statistical learning (or double ML) has been accepted at COLT 2022.
  • 04/30/2022: A new preprint on orthogonal statistical learning is available at arXiv.
  • 03/30/2022: Oral presentation at AISTATS 2022 on entropy regularized optimal transport independence criterion.
  • 03/18/2022: Presentation at Kantorovich Initiative Retreat on entropy regularized optimal transport independence criterion.
  • 02/04/2022: A new preprint on meta-learning is available at arXiv.
  • 01/21/2022: Presentation at ML-Opt on statistical analysis of divergence frontiers.
  • 12/13/2021: Our paper on discrete Schrödinger bridges and two-sample testing has received the Best Paper Award at NeurIPS 2021 OTML Workshop.
  • 09/28/2021: Our paper on statistical analysis of divergence frontiers has been accepted at NeurIPS 2021.