Pith. sign in

REVIEW 3 cited by

A Primer on Private Statistics

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 2005.00010 v1 pith:LSTGJMDV submitted 2020-04-30 stat.ML cs.CRcs.DScs.ITcs.LGmath.IT

classification stat.MLcs.CRcs.DScs.ITcs.LGmath.IT
keywords statisticsempiricalpopulationprivateworkappliedareabeen
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Differentially private statistical estimation has seen a flurry of developments over the last several years. Study has been divided into two schools of thought, focusing on empirical statistics versus population statistics. We suggest that these two lines of work are more similar than different by giving examples of methods that were initially framed for empirical statistics, but can be applied just as well to population statistics. We also provide a thorough coverage of recent work in this area.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Sequential Auditing for f-Differential Privacy

    cs.CR 2026-02 conditional novelty 7.0 of 10

    A new sequential auditor for f-differential privacy adaptively chooses its sample size, detects violations across the whole privacy tradeoff curve, and holds a user-set false-rejection rate.

  2. Privacy in Metalearning and Multitask Learning: Modeling and Separations

    cs.LG 2024-12 conditional novelty 7.0 of 10

    The paper proves a formal separation between joint differential privacy and billboard or metalearning privacy, showing that the public billboard model can require far more data.

  3. How Private is Your Attention? Bridging Privacy with In-Context Learning

    stat.ML 2025-04 conditional novelty 6.0 of 10

    Differentially private pretraining of linear attention heads for in-context linear regression has excess risk that decays like 1/(N L^3) in low dimensions and D^2/(N^2 L^2) in high dimensions, up to log factors and pr...

Pith tools