The paper proves a formal separation between joint differential privacy and billboard or metalearning privacy, showing that the public billboard model can require far more data.
write newline
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Privacy in Metalearning and Multitask Learning: Modeling and Separations
The paper proves a formal separation between joint differential privacy and billboard or metalearning privacy, showing that the public billboard model can require far more data.