A two-step reweighted ℓ1-minimization algorithm for sparse subspace clustering is introduced along with analytic probability bounds on neighbor recovery under the semi-random model.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Proves weak and strong duality between function-space and measure-space convex relaxations of constrained variational problems, establishing their equivalence for SDP hierarchy computations when data are polynomial.
citing papers explorer
-
Sparse Subspace Clustering via Two-Step Reweighted L1-Minimization: Algorithm and Provable Neighbor Recovery Rates
A two-step reweighted ℓ1-minimization algorithm for sparse subspace clustering is introduced along with analytic probability bounds on neighbor recovery under the semi-random model.
-
Duality of convex relaxations for constrained variational problems
Proves weak and strong duality between function-space and measure-space convex relaxations of constrained variational problems, establishing their equivalence for SDP hierarchy computations when data are polynomial.