Empirical study of DP transfer learning reveals that larger clipping bounds outperform under tight privacy and cumulative DP noise explains batch-size effects better than existing heuristics.
Ruixuan Liu and Zhiqi Bu
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On Optimal Hyperparameters for Differentially Private Deep Transfer Learning
Empirical study of DP transfer learning reveals that larger clipping bounds outperform under tight privacy and cumulative DP noise explains batch-size effects better than existing heuristics.