SMA-DP-SGD augments DP-SGD with a spectral memory-aware fractional branch from prior privatized updates to improve accuracy on CIFAR and MNIST while preserving conditional differential privacy.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Gradient alignment persists throughout multi-step distillation training and causally drives unintended teacher trait acquisition in the student, while liminal training attenuates alignment but does not stop the acquisition.
Standard NLP classifiers can surface valid injury precursors from raw construction safety reports.
citing papers explorer
-
SMA-DP: Spectral Memory-Aware Differential Privacy for Deep Learning
SMA-DP-SGD augments DP-SGD with a spectral memory-aware fractional branch from prior privatized updates to improve accuracy on CIFAR and MNIST while preserving conditional differential privacy.
-
Sustained Gradient Alignment Mediates Subliminal Learning in a Multi-Step Setting: Evidence from MNIST Auxiliary Logit Distillation Experiment
Gradient alignment persists throughout multi-step distillation training and causally drives unintended teacher trait acquisition in the student, while liminal training attenuates alignment but does not stop the acquisition.
-
Automatically Learning Construction Injury Precursors from Text
Standard NLP classifiers can surface valid injury precursors from raw construction safety reports.