Privately Learning Markov Random Fields

by   Huanyu Zhang, et al.

We consider the problem of learning Markov Random Fields (including the prototypical example, the Ising model) under the constraint of differential privacy. Our learning goals include both structure learning, where we try to estimate the underlying graph structure of the model, as well as the harder goal of parameter learning, in which we additionally estimate the parameter on each edge. We provide algorithms and lower bounds for both problems under a variety of privacy constraints – namely pure, concentrated, and approximate differential privacy. While non-privately, both learning goals enjoy roughly the same complexity, we show that this is not the case under differential privacy. In particular, only structure learning under approximate differential privacy maintains the non-private logarithmic dependence on the dimensionality of the data, while a change in either the learning goal or the privacy notion would necessitate a polynomial dependence. As a result, we show that the privacy constraint imposes a strong separation between these two learning problems in the high-dimensional data regime.


page 1

page 2

page 3

page 4


Property Testing for Differential Privacy

We consider the problem of property testing for differential privacy: wi...

Pure Differential Privacy from Secure Intermediaries

Recent work in differential privacy has explored the prospect of combini...

A normal approximation for joint frequency estimatation under Local Differential Privacy

In the recent years, Local Differential Privacy (LDP) has been one of th...

Bisimilarity Distances for Approximate Differential Privacy

Differential privacy is a widely studied notion of privacy for various m...

Learning with Differential Privacy: Stability, Learnability and the Sufficiency and Necessity of ERM Principle

While machine learning has proven to be a powerful data-driven solution ...

Toward Detecting Violations of Differential Privacy

The widespread acceptance of differential privacy has led to the publica...

Network change point localisation under local differential privacy

Network data are ubiquitous in our daily life, containing rich but often...