TP-TopK uses private warm-up to select k coordinates for DP-SGD, with a stationarity bound showing noise scales with k (not d) under a given criterion, and experiments on image datasets showing learned supports retain more gradient energy than random ones.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CAPS provides an iterative differentially private synthesis method that outperforms one-shot baselines on authentic educational real-world data.
citing papers explorer
-
When Do Fewer Coordinates Suffice in DP-SGD?
TP-TopK uses private warm-up to select k coordinates for DP-SGD, with a stationarity bound showing noise scales with k (not d) under a given criterion, and experiments on image datasets showing learned supports retain more gradient energy than random ones.
-
Cyclic Adaptive Private Synthesis for Sharing Real-World Data in Education
CAPS provides an iterative differentially private synthesis method that outperforms one-shot baselines on authentic educational real-world data.