Victor Veitch

I am a research scientist interested in the theory and application of machine learning and statistical inference, particularly in situations where the current tools are lacking or nonexistant.

I'm currently a postdoc in the department of statistics at Columbia University, where I work 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.

Much of my work revolves around learning from relational data such as networks. Other recent interests include causal inference, stochastic optimization, privacy, and probabilistic symmetries.

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

News and Travel

  • New preprint generalizing empirical risk minimization to relational data
  • New preprint connecting compression and generalization in deep learning
  • I won the 2018 Pierre Robillard award for the best PhD thesis in probability or statistics defended at a Canadian university

Curriculum Vitae