ROSU derives a closed-form retain-neutral perturbation for min-max unlearning that bounds retain damage via curvature and improves performance when gradients are aligned.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
DPS quantifies deviation of per-sample decision patterns from class averages and shows linear correlation with generalization gaps while unifying degradation scenarios into a continuous trajectory.
SleepNet and DreamNet enrich visual features via supervised pre-trained encoders and reconstruct hidden states with encoder-decoder frameworks to outperform prior state-of-the-art classifiers.
citing papers explorer
-
Retain-Neutral Surrogates for Min-Max Unlearning
ROSU derives a closed-form retain-neutral perturbation for min-max unlearning that bounds retain damage via curvature and improves performance when gradients are aligned.
-
Understanding Generalization through Decision Pattern Shift
DPS quantifies deviation of per-sample decision patterns from class averages and shows linear correlation with generalization gaps while unifying degradation scenarios into a continuous trajectory.
-
SleepNet and DreamNet: Enriching and Reconstructing Representations for Consolidated Visual Classification
SleepNet and DreamNet enrich visual features via supervised pre-trained encoders and reconstruct hidden states with encoder-decoder frameworks to outperform prior state-of-the-art classifiers.