Masking-based explanations are query-channel communication: recovery fails above identification capacity and a sparse ML decoder succeeds below it, while LIME/SHAP-style surrogates lag.
Compressed sensing
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Refines Cover's dichotomy counts and separation capacity for low-dimensional data by adjusting the general position assumption.
SPP-SBL unifies pattern-based block sparse Bayesian learning via a variance transformation framework and introduces a space-power prior to adaptively capture unknown block structures while solving space coupling parameter estimation with EM and root-solving.
citing papers explorer
-
The Query Channel: Information-Theoretic Limits of Masking-Based Explanations
Masking-based explanations are query-channel communication: recovery fails above identification capacity and a sparse ML decoder succeeds below it, while LIME/SHAP-style surrogates lag.
-
Function-Counting Theory for Low-Dimensional Data Structures
Refines Cover's dichotomy counts and separation capacity for low-dimensional data by adjusting the general position assumption.
-
SPP-SBL: Space-Power Prior Sparse Bayesian Learning for Block Sparse Recovery
SPP-SBL unifies pattern-based block sparse Bayesian learning via a variance transformation framework and introduces a space-power prior to adaptively capture unknown block structures while solving space coupling parameter estimation with EM and root-solving.