GAE reduces the faithfulness gap in dictionary-based explainers under distribution shift by geometrically realigning the ID dictionary to the OOD-active subspace, with a quadratic excess-loss bound.
A useful variant of the davis–kahan theorem for statisticians
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
ULSE extends spectral embedding using normalized Laplacians with proven cross-sectional and longitudinal stability plus a dynamic Cheeger inequality under dynamic stochastic block models.
MiMuon is a hybrid optimizer that achieves a generalization error bound of O(1/N) independent of the small singular-value gap that limits the original Muon bound, while retaining the same O(1/T^{1/4}) convergence rate.
citing papers explorer
-
Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
GAE reduces the faithfulness gap in dictionary-based explainers under distribution shift by geometrically realigning the ID dictionary to the OOD-active subspace, with a quadratic excess-loss bound.
-
Unfolded Laplacian Spectral Embedding: A Theoretically Grounded Approach to Dynamic Network Representation
ULSE extends spectral embedding using normalized Laplacians with proven cross-sectional and longitudinal stability plus a dynamic Cheeger inequality under dynamic stochastic block models.
-
MiMuon: Mixed Muon Optimizer with Improved Generalization for Large Models
MiMuon is a hybrid optimizer that achieves a generalization error bound of O(1/N) independent of the small singular-value gap that limits the original Muon bound, while retaining the same O(1/T^{1/4}) convergence rate.