Victor's research on sparse graph models, graph limits, and estimation has made foundational contributions to network data analysis and more generally, the problem of modeling relational data. The key technical challenge in this setting is that standard statistical assumptions do not hold. Victor's thesis starts by adopting a natural invariance principle, which then yields a new class of random graph models. This new model contains the popular stochastic block model (indeed, every exchangeable graph model) as a submodel, but also permits sparsely connected graphs, which are believed to better capture the statistics of real-world networks. Victor's thesis makes an in-depth study of this new model, uncovering sampling interpretations and identifying canonical estimators. His work also makes substantial contributions to the theory of graph limits.

Victor is from Waterloo, Ontario. He earned a BSc in mathematical physics from the University of Waterloo, and later earned a MMath, also from Waterloo, working in quantum computation. Victor is currently a Distinguished Postdoctoral Fellow in Statistics at Columbia University.

The criteria used in selecting the winner of the Pierre Robillard Award include the originality of ideas and techniques, the possible applications and their treatment, and the potential impact of the work. The award is named in memory of Professor Pierre Robillard, an outstanding dynamic young statistician at the Université de Montréal, whose untimely death in 1975 cut short what promised to be a highly distinguished career.

Victor Veitch will present an overview of his work in a special session at this year’s SSC Annual Meeting at McGill University.