↓Skip to main content

On the Identifiability of Tensor Ranks via Prior Predictive Matching

·61 words
Eliezer De Souza Da Silva Arto Klami Diego Mesquita Iñigo Urteaga Publication Conference AISTATS Tensor Factorization Bayesian Modeling Identifiability

A principled framework for tensor rank identifiability based on prior predictive moment matching, with closed-form estimators for identifiable tensor models.

AISTATS 2026

Publication

  • Eliezer de Souza da Silva, Arto Klami, Diego Mesquita, Iñigo Urteaga. On the Identifiability of Tensor Ranks via Prior Predictive Matching. The 29th International Conference on Artificial Intelligence and Statistics (AISTATS 2026).

Links

Extras Bibtex