arXiv (All)
open access
Actually, All Learnable Distribution Classes Are Privately Learnable
We show that every class of distributions that is learnable up to arbitrarily small target error in total variation distance with finitely many samples is also learnable under ($\varepsilon, δ$)-differential privacy up to arbitrarily small target error with finitely many samples. This proves a conje
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Differentially Private Sampling from Distributions via Wasserstein Projection#175142
- Faster Learning under Relaxed Local Differential Privacy#971989
- Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning#609724
- Symmetry Guarantees Statistic Recovery in Variational Inference#120540
- Contraction and Statistical Inference under Privacy for Uniformly Bounded Distributions#1064841
Record · ID 1413119
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive