Polynomial time and private learning of unbounded Gaussian Mixture Models
Bibliographic record
Abstract
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.003 | 0.008 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.002 | 0.006 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".