Proposes a structured transform learning method via inexact proximal optimization with a closed-form projection, claiming SOTA results on doubly sparse learning at lower cost than dense variants.
Sparsifying transform learning with efficient optimal updates and convergence guarantees
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning Doubly Sparse Explicitly Conditioned Transforms
Proposes a structured transform learning method via inexact proximal optimization with a closed-form projection, claiming SOTA results on doubly sparse learning at lower cost than dense variants.