Optimal reconstruction error from approximate linear queries converges to sqrt(2d/(d+1)) delta as number of queries T goes to infinity, with doubly exponential excess error decay for fixed d and exp(d) queries needed for vanishing excess when d grows.
Calibrating Noise to Sensitivity in Private Data Analysis , Volume =
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
-
Optimal Reconstruction from Linear Queries
Optimal reconstruction error from approximate linear queries converges to sqrt(2d/(d+1)) delta as number of queries T goes to infinity, with doubly exponential excess error decay for fixed d and exp(d) queries needed for vanishing excess when d grows.