Pith. sign in

REVIEW

Training generative models from privatized data

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.09547 v2 pith:GRVUFVGW submitted 2023-06-15 cs.LG cs.CRcs.ITmath.IT

classification cs.LGcs.CRcs.ITmath.IT
keywords dataprivatizedregularizationconvergenceenablesentropicframeworkgenerative
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Local differential privacy is a powerful method for privacy-preserving data collection. In this paper, we develop a framework for training Generative Adversarial Networks (GANs) on differentially privatized data. We show that entropic regularization of optimal transport - a popular regularization method in the literature that has often been leveraged for its computational benefits - enables the generator to learn the raw (unprivatized) data distribution even though it only has access to privatized samples. We prove that at the same time this leads to fast statistical convergence at the parametric rate. This shows that entropic regularization of optimal transport uniquely enables the mitigation of both the effects of privatization noise and the curse of dimensionality in statistical convergence. We provide experimental evidence to support the efficacy of our framework in practice.

Discussion (0). Continue with ORCID to comment.

Pith tools