MétaCan
Menu
Back to cohort
Record W7014515766

Polynomial time and private learning of unbounded Gaussian Mixture Models

2023· dissertation· en· W7014515766 on OpenAlexaff

Bibliographic record

VenueMacSphere (McMaster University) · 2023
Typedissertation
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsMcMaster University
Fundersnot available
KeywordsOverhead (engineering)Mixture modelTime complexityPolynomialGaussianComputational complexity theoryEstimatorSample complexity
DOInot available

Abstract

fetched live from OpenAlex

We develop a technique for privately estimating the parameters of a mixture distribution by reducing the problem to its non-private counterpart. This technique allows us to privatize existing non-private algorithms in a BlackBox manner while only incurring a small overhead in sample complexity and running time. As the main application of our framework, we develop an algorithm for privately learning mixtures of Gaussians using the non-private algorithm of Moitra and Valiant [MV10] as a BlackBox and incurs only a polynomial time overhead in the sample complexity and computational complexity. As a result, this gives the first sample complexity upper bound and the first polynomial time algorithm in d for learning the parameters of the Gaussian Mixture Models privately without requiring any boundedness assumptions on the parameters. To prove the results we introduced Private Populous Estimator (PPE) which is a generalized version of the one used in [AL22] to achieve (ϵ, δ)-differential privacy. We also develop a new masking mechanism for a single Gaussian component. Then we introduce a general recipe to turn a masking mechanism for a component into a masking mechanism for mixtures.

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)0.006
metaresearch head score (Gemma)0.024
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 score0.006
Threshold uncertainty score0.031

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.024
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0010.001
Science and technology studies0.0010.003
Scholarly communication0.0030.008
Open science0.0030.006
Research integrity0.0020.006
Insufficient payload (model declined to judge)0.0030.001

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 head0.017
GPT teacher head0.219
Teacher spread0.202 · 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

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueMacSphere (McMaster University)Same topicPrivacy-Preserving Technologies in DataFrench-language works237,207