Piotr Zwiernik

Department of Statistical Sciences,
Department of Mathematics,
University of Toronto

Contact:University of Toronto
Department of Statistical Sciences
9th Floor, Ontario Power Building
700 University Ave
Toronto, ON M5G 1Z5
Office: 9133
E-mail: piotr.zwiernik@utoronto.ca

Gaussian tripod

Research interests: high-dimensional covariance matrix estimation, graphical models, convex optimization, algebraic and combinatorial methods in statistics.

Editorial responsibilities: Biometrika, Scandinavian Journal of Statistics, Algebraic Statistics.


  • We just got a paper out on Non-independent component analysis defining some new tensor problems and proposing an efficient alternative to ICA in the case where independence cannot be assumed.
  • IMSI program on Algebraic Statistics: consider applying for a visiting position. More information on the accompanying workshops will follow shortly.
  • I am looking for undergraduate and graduate students interested in mathematical statistics and its aspects related to combinatorics, convex analysis, and tensors. For recent PhD graduates: There is a number of open calls for postdoctoral positions at UofT - see here, here, here, here, and here (the latter is particularly suitable for underrepresented groups).
  • GOLAZO R package for a general assymetric regularization of the log-likelihood in Gaussian graphical models.
    To install, just call in R: devtools::install_github("pzwiernik/golazo")

Math to the people (four axioms of Federico Ardila):

  • Axiom 1. Mathematical potential is distributed equally among different groups, irrespective of geographic, demographic, and economic boundaries.
  • Axiom 2. Everyone can have joyful, meaningful, and empowering mathematical experiences.
  • Axiom 3. Mathematics is a powerful, malleable tool that can be shaped and used differently by various communities to serve their needs.
  • Axiom 4. Every student deserves to be treated with dignity and respect.

I am on leave from:

Department of Economics and Business
Universitat Pompeu Fabra

BSE Data Science Center

Statistics group at UPF