Pith. sign in

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

arxiv 2301.13273 v1 pith:3MAO75GE submitted 2023-01-30 cs.LG cs.CRmath.STstat.MLstat.TH

classification cs.LGcs.CRmath.STstat.MLstat.TH
keywords algorithmlinearregressionapproachcomplexitydeltadescentgradient
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. On the Benefits of Accelerated Optimization in Robust and Private Estimation

    math.ST 2025-06 conditional novelty 6.0 of 10

    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}.

Pith tools