For multiple instance regression and learning from label proportions, optimal data bagging for linear regression reduces approximately to k-means clustering over labels or features, and the mechanisms can be made label-differentially private with a quantified utility cost.
PAC learning linear thresholds from label proportions
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
-
Aggregating Data for Optimal and Private Learning
For multiple instance regression and learning from label proportions, optimal data bagging for linear regression reduces approximately to k-means clustering over labels or features, and the mechanisms can be made label-differentially private with a quantified utility cost.