A differentially private fine-tuning method that constructs a quadratic utility function to allow exact sampling from a multivariate normal distribution while providing theoretical privacy guarantees.
Are normalizing flows the key to unlocking the exponential mechanism? a path through the accuracy-privacy ceiling constraining differentially private ml
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees
A differentially private fine-tuning method that constructs a quadratic utility function to allow exact sampling from a multivariate normal distribution while providing theoretical privacy guarantees.