MétaCan
Menu
Back to cohort
Record W2567588361 · doi:10.4230/lipics.socg.2017.45

Lower Bounds for Differential Privacy from Gaussian Width

2017· article· en· W2567588361 on OpenAlexaff
Assimakis Kattis, Aleksandar Nikolov

Bibliographic record

VenueDROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2017
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsDifferential privacyPolytopeGaussianWorkloadConvex geometrySample (material)Measure (data warehouse)MathematicsConvex bodySensitivity (control systems)Upper and lower boundsRegular polygonComputer scienceDiscrete mathematicsAlgorithmConvex optimizationConvex setMathematical analysisDatabaseGeometry

Abstract

fetched live from OpenAlex

We study the optimal sample complexity of a given workload of linear queries under the constraints of differential privacy. The sample complexity of a query answering mechanism under error parameter alpha is the smallest n such that the mechanism answers the workload with error at most alpha on any database of size n. Following a line of research started by Hardt and Talwar [STOC 2010], we analyze sample complexity using the tools of asymptotic convex geometry. We study the sensitivity polytope, a natural convex body associated with a query workload that quantifies how query answers can change between neighboring databases. This is the information that, roughly speaking, is protected by a differentially private algorithm, and, for this reason, we expect that a "bigger" sensitivity polytope implies larger sample complexity. Our results identify the mean Gaussian width as an appropriate measure of the size of the polytope, and show sample complexity lower bounds in terms of this quantity. Our lower bounds completely characterize the workloads for which the Gaussian noise mechanism is optimal up to constants as those having asymptotically maximal Gaussian width. Our techniques also yield an alternative proof of Pisier's Volume Number Theorem which also suggests an approach to improving the parameters of the theorem.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.010
metaresearch head score (Gemma)0.088
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.010
Threshold uncertainty score0.055

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0100.088
Meta-epidemiology (narrow)0.0030.001
Meta-epidemiology (broad)0.0040.003
Bibliometrics0.0030.003
Science and technology studies0.0020.006
Scholarly communication0.0070.019
Open science0.0050.007
Research integrity0.0030.009
Insufficient payload (model declined to judge)0.0070.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.030
GPT teacher head0.290
Teacher spread0.260 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2017
Admission routes1
Has abstractyes

Explore more

Same venueDROPS (Schloss Dagstuhl – Leibniz Center for Informatics)Same topicPrivacy-Preserving Technologies in DataFrench-language works237,207