Victor Veitch

I'm an assistant professor of Statistics and Data Science at the University of Chicago (as of Jan 1, 2021) and a research scientist at Google Cambridge.

My research is primarily on machine learning. My recent work revolves around the intersection of machine learning and causal inference. I'm interested in the design and evaluation of safe and credible AI systems. Other particular interests include network data, and the foundations of learning and statistical inference.

I was previously a Distinguished Postdoctoral Researcher in the department of statistics at Columbia University, where I worked with the groups of David Blei and Peter Orbanz. I completed my Ph.D. in statistics at the University of Toronto, where I was advised by Daniel Roy. In a previous life, I worked on quantum computing at the University of Waterloo.

I like collaborations; reach out if you've got a cool problem you'd like to chat about!


  • New preprint on how the use of instrumental variables with many candidate instruments. We consider the case where some of the instruments may be invalid. Key idea: we achieve robustness to invalidity by estimating the effect using each instrument and reporting the median.
  • New preprint on how to assess bias due to unobserved confounding in causal estimation. Key points: the method is very simple, and avoids putting any restrictions on how the observed data is modeled. Comments very welcome!
  • Our paper showing how to do causal inference with text data by exploiting deep natural language models is accepted at UAI

Curriculum Vitae