A piecewise biconvex optimization framework unifies sparse dictionary learning variants, explains their pathologies via spurious optima, and enables feature anchoring to restore identifiability.
African Grey
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima
A piecewise biconvex optimization framework unifies sparse dictionary learning variants, explains their pathologies via spurious optima, and enables feature anchoring to restore identifiability.