MétaCan
Menu
Back to cohort
Record W7018926123

Efficient and Differentially Private Statistical Estimation via a Sum-of-Squares Exponential Mechanism

2022· dissertation· en· W7018926123 on OpenAlexaff

Bibliographic record

VenueUWSpace (University of Waterloo) · 2022
Typedissertation
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsBlackberry (Canada)
Fundersnot available
KeywordsRobustness (evolution)Probability distributionExponential functionDifferential privacyGaussianStatistical distanceConnection (principal bundle)HierarchyExponential family
DOInot available

Abstract

fetched live from OpenAlex

As machine learning is applied to more privacy-sensitive data, it is becoming increasingly crucial to develop algorithms that maintain privacy. However, even the most basic high-dimensional statistical estimation tasks were not fully understood under differential privacy, specifically, there were no known efficient algorithms for mean estimation using the optimal number of samples under pure differential privacy. \n \nWe propose a new method for designing efficient and information-theoretically optimal algorithms for statistical estimation tasks that preserve privacy, using a combination of the Sum-of-Squares hierarchy and the exponential mechanism. The Sum-of-Squares hierarchy, a convex programming method, has been used to design efficient algorithms in robust statistics. The exponential mechanism, which has been widely used in differential privacy, is often used to design information-theoretically optimal algorithms, but can be inefficient. By combining these two approaches, we are able to create efficient algorithms that are also information-theoretically optimal. We apply this approach to mean estimation for heavy-tailed distributions and learning Gaussian distributions and achieve optimal results. We also show that this approach can be applied to other problems captured by the Sum-of-Squares hierarchy through a meta-theorem. Additionally, our algorithms highlight the strong connection between robustness and privacy. \n \nWe establish information-theoretical lower bounds to show the statistical optimality of our approaches. Technically we use packing lower bounds; however, the novelty of our lower bounds is in capturing the high probability setting.

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)0.013
metaresearch head score (Gemma)0.048
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: Methods · Consensus signal: Methods
Teacher disagreement score0.013
Threshold uncertainty score0.067

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0130.048
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0030.002
Bibliometrics0.0010.003
Science and technology studies0.0010.004
Scholarly communication0.0040.009
Open science0.0050.009
Research integrity0.0030.007
Insufficient payload (model declined to judge)0.0030.002

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 head0.011
GPT teacher head0.221
Teacher spread0.210 · 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
GenreMethods

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

Citations0
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueUWSpace (University of Waterloo)Same topicPrivacy-Preserving Technologies in DataFrench-language works237,207