HYVINT introduces an intensity-driven incidence mechanism and tractable variational estimator for hypergraph generation, with error bounds and empirical gains in fidelity, novelty, and diversity.
Algorithms for non-negative matrix factorization.Advances in neural information processing systems, 13
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Convergence analysis for proximal gradient-type methods with arbitrary proximal terms in nonconvex composite optimization, without requiring the global descent property between the smooth function and its proximal mapping.
citing papers explorer
-
HYVINT: Intensity-Driven Hypergraph Generation with Variational Representations
HYVINT introduces an intensity-driven incidence mechanism and tractable variational estimator for hypergraph generation, with error bounds and empirical gains in fidelity, novelty, and diversity.
-
Proximal gradient-type method with generalized distance and convergence analysis without global descent lemma
Convergence analysis for proximal gradient-type methods with arbitrary proximal terms in nonconvex composite optimization, without requiring the global descent property between the smooth function and its proximal mapping.