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.
Gy¨ orgyi, Inference of a rule by a neural network with thermal noise, Physical review letters64(24), 2957 (1990)
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.