The paper proposes message-passing algorithms and a replica theory using cumulant expansion for tensor factorization inference in a dense limit on random graphs, avoiding Gaussian assumptions.
Reeves, Information-theoretic limits for the matrix tensor product, IEEE Journal on Selected Areas in Information Theory1(3), 777 (2020)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Graphical model for factorization and completion of relatively high rank tensors by sparse sampling
The paper proposes message-passing algorithms and a replica theory using cumulant expansion for tensor factorization inference in a dense limit on random graphs, avoiding Gaussian assumptions.