Random orthonormal matrices are minimax optimal for sketched least squares and rotation-invariant embeddings for randomized SVD, yielding the sharpest error bounds.
Distributed sketching methods for privacy preserving regression
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
NDIS lemma computes closed-form hockey-stick divergence δ(ε) between arbitrary multivariate Gaussians and is applied to obtain tighter privacy for random projection.
citing papers explorer
-
Sharp analysis of sketched least squares and randomized low-rank approximation
Random orthonormal matrices are minimax optimal for sketched least squares and rotation-invariant embeddings for randomized SVD, yielding the sharpest error bounds.
-
The Normal Distributions Indistinguishability Spectrum and its Application to Privacy-Preserving Machine Learning
NDIS lemma computes closed-form hockey-stick divergence δ(ε) between arbitrary multivariate Gaussians and is applied to obtain tighter privacy for random projection.