REVIEW 1 cited by
Near Optimal Private and Robust Linear Regression
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
We study the canonical statistical estimation problem of linear regression from $n$ i.i.d.~examples under $(\varepsilon,\delta)$-differential privacy when some response variables are adversarially corrupted. We propose a variant of the popular differentially private stochastic gradient descent (DP-SGD) algorithm with two innovations: a full-batch gradient descent to improve sample complexity and a novel adaptive clipping to guarantee robustness. When there is no adversarial corruption, this algorithm improves upon the existing state-of-the-art approach and achieves a near optimal sample complexity. Under label-corruption, this is the first efficient linear regression algorithm to guarantee both $(\varepsilon,\delta)$-DP and robustness. Synthetic experiments confirm the superiority of our approach.
Forward citations
Cited by 1 Pith paper
-
On the Benefits of Accelerated Optimization in Robust and Private Estimation
Momentum-accelerated Frank-Wolfe and gradient descent reduce both iteration counts and privacy noise for private and heavy-tailed-robust estimation, yielding rates such as 1/(nε) instead of 1/(nε)^{2/3}.
Discussion (0). Continue with ORCID to comment.