Quanhan (Johnny) Xi

profile.jpg

I am a Ph. D. Student in the Department of Statistics at the University of British Columbia, supervised by Ben Bloem-Reddy. Recently, I have been interested in causal discovery, generative modelling, and their application in high-throughput biology. I have also been an intern with Jason Hartford at Valence Labs, where I worked on causal representation learning and multimodality.

news

May 1, 2024 We have a paper from my time at Valence accepted as a spotlight presentation at the MLGenX workshop on using propensity scores to align unpaired samples. In biology, you can in theory have multimodal measurements of the same cell in biology, but each measurement process is destructive, putting us naturally in a “potential outcomes” setting. See the preprint on arXiv!
Dec 4, 2023 I will be presenting a poster at the CRL workshop on triangular monotonic maps for causal discovery. See the paper.
Nov 22, 2023 I gave a talk on the statistical modelling aspects of identifiability in generative models at the CARE reading group, organized by Valence Labs. There is a recording available on YouTube!

selected publications

  1. ICLR MLGenX
    Propensity Score Alignment of Unpaired Multimodal Data
    Johnny Xi, and Jason Hartford
    In ICLR 2024 Workshop on Machine Learning for Genomics Explorations, 2024
  2. AISTATS
    Indeterminacy in Generative Models: Characterization and Strong Identifiability
    Quanhan Xi, and Benjamin Bloem-Reddy
    In AISTATS, 2023