Probabilistic Tensor Factorization and Model Selection

Cyril Goutte, Massih-Reza Amini
National Research Council Canada
123, boulevard Alexandre Taché
Gatineau, Canada

The well-known formal equivalence between non-negative matrix factorization and multinomial mixture models extends in a fairly straightforward manner to tensors. Among interesting practical implications of this equivalence, this suggests some principled ways to choose the number of factors in the decomposition. We discuss and illustrate two methods to do this in Postive Tensor Factorization.