
Global Identifiability of L1-based Dictionary Learning via Matrix Volume Optimization
Establishes global identifiability guarantees for L1-based dictionary learning via a matrix-volume formulation.
For a complete and current list, see my Google Scholar profile.

Establishes global identifiability guarantees for L1-based dictionary learning via a matrix-volume formulation.

Introduces a minimum-volume enclosing parallelotope view for identifiable bounded component analysis.

Provides identifiability analysis and an efficient algorithm for complex-valued bounded component analysis.