Matrix-valued data can be clustered by a convex objective that fuses centroids and penalizes their nuclear norms, with exact and asymptotic recovery guarantees and finite-sample error bounds.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Low Rank Convex Clustering For Matrix-Valued Observations
Matrix-valued data can be clustered by a convex objective that fuses centroids and penalizes their nuclear norms, with exact and asymptotic recovery guarantees and finite-sample error bounds.